{"as_of":"2026-08-08T11:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e93348584eee3b1d7896477fdf2f5a2765c3da6c3c873d3d0ce324e74645cec6","coverage":[{"denominator":70,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":70,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:52:08.054810Z","state":"measured"},{"denominator":70,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":70,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.04453/citation-record","integrity":"/paper/2506.04453/integrity","json":"/paper/2506.04453/citation-record.json","paper":"/paper/2506.04453"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.552964Z","title":"Goodfellow, H","venue":null,"work_id":"3748d152-95f9-4a80-a81d-a1e2f09b1598","year":2016},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.897655Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:ea55a6b7f13c4d01e17a1bfe353ddc97f451ce722ced769fe087b003f1ce20ea","observation_id":"6f6b65c3-f768-45c0-9319-253dd19934e4","resolution":{"observed_at":"2026-08-07T10:52:08.555192Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.546375Z","title":null,"venue":null,"work_id":"594c6741-b872-401a-899e-751a256a33b2","year":2024},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.900582Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:fb04eec140ab024b987ad32e89a0751bf527f59359fda1ac77981beac8685cb2","observation_id":"e2de3b2d-c116-48a3-9b1b-c0da2d7ac9e7","resolution":{"observed_at":"2026-08-07T10:52:08.548582Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.539642Z","title":"QSGD: communication-efficient SGD via gradient quantization and encoding","venue":null,"work_id":"418b1632-19ff-49b9-ac96-6ef2ea0d8b6e","year":2017},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.902977Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:23fd50dd7fcc82e2e998486256f3fcadee23478f0df6249b1ce0da493474e402","observation_id":"5a32beb4-18f2-4471-83f5-265d3908d71c","resolution":{"observed_at":"2026-08-07T10:52:08.542030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.532970Z","title":"The con- vergence of sparsified gradient methods","venue":null,"work_id":"23d5941a-c8d1-4e88-b562-2e769c2fa6f1","year":2018},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.905394Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:173cb1d0bb2f88130be80cd9381014737ea6c516e430ed44274ef1cd221310ba","observation_id":"e0ec741c-f351-4e52-81cd-0e8e07afd5f6","resolution":{"observed_at":"2026-08-07T10:52:08.535222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.526376Z","title":"When the curious abandon honesty: Federated learning is not private","venue":null,"work_id":"0f2334f7-680c-40f5-bfe3-2215a9dda880","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.907931Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:dc9ea20b1782b59cf14246789cf92497d02465587dfbb50f90dc697868038a0b","observation_id":"32e0af99-40b3-4a73-9e22-97866bf10b8e","resolution":{"observed_at":"2026-08-07T10:52:08.528640Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.519591Z","title":"Tinytl: Reduce memory, not parameters for efficient on-device learning","venue":null,"work_id":"596c8a7f-e487-4ee6-bdff-1a7879b3cfd9","year":2020},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.910349Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:196c0b6fabfbe0a67a0cada45a950a5f76107d69abf01a95d1227c162cb8f09c","observation_id":"c881627c-7884-4032-9550-87d48c37e5c3","resolution":{"observed_at":"2026-08-07T10:52:08.522066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.513019Z","title":"Brown, Dawn Song, ´Ulfar Erlingsson, Alina Oprea, and Colin Raffel","venue":null,"work_id":"b3409eeb-924c-4e4f-a2b7-cc71b5b5828a","year":2021},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.912831Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:6220bc0f96f0d05c547cda45c8a1b67f6278879a7a8c97a18987085da984b254","observation_id":"e26e6572-1a6b-4f08-82b6-ed48fc7d1af1","resolution":{"observed_at":"2026-08-07T10:52:08.515214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.506632Z","title":"Adaptformer: Adapting vision transformers for scalable visual recogni- tion","venue":null,"work_id":"5a86c306-d3ca-4ce2-a23f-27619594408e","year":2022},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.915009Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:b5fd92d432b978e28fa8d260841e6ca2f854df5382d24d30ce37d76bcb158fde","observation_id":"06380ba4-f6c2-4ebd-998d-37e6a70d51c9","resolution":{"observed_at":"2026-08-07T10:52:08.508824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.499831Z","title":"The janus interface: How fine-tuning in large language models amplifies the privacy risks","venue":null,"work_id":"8997edbe-6ab7-4adb-9add-cc34e3a05330","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.917191Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:ca79dbc287254dc5a105fc266190a4c98f57dfe2683db383eea0c4fa65eca575","observation_id":"b0f9c0be-1d31-4f10-86be-a42a994f57f8","resolution":{"observed_at":"2026-08-07T10:52:08.502194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.493374Z","title":"Fowl, Micah Gold- blum, and Tom Goldstein","venue":null,"work_id":"a276080b-2886-48e5-9102-4d9b1a60b717","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.919374Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:da7b92fffd872df65a00c1a04516bce97b098703bad656e686987b0cec088275","observation_id":"abac8ffe-9502-42ed-b4a3-d244cdb932e6","resolution":{"observed_at":"2026-08-07T10:52:08.495541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.486832Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":"83c575ff-5c64-42ea-948a-4a708b64ff99","year":2009},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.921642Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:d66910843e872823ea9e201fa8bd9f1c33cc0834dca65d02c3af2869cb0ef8f6","observation_id":"d152c830-ff40-4156-94b0-5220e1349d29","resolution":{"observed_at":"2026-08-07T10:52:08.489154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.480007Z","title":"Effi- cient adaptation of large vision transformer via adapter re- composing","venue":null,"work_id":"410751bc-0ab9-49d2-85c6-5aab24912cc3","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.923640Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:ea7ff683013f7a09479fdb7597903b583ae9c62e1c213aa43b23f94e2c32b7e3","observation_id":"ed8f9e5b-289b-4a4a-8276-9502afcec776","resolution":{"observed_at":"2026-08-07T10:52:08.482394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.473168Z","title":"Low-rank rescaled vision transformer fine-tuning: A residual design approach","venue":null,"work_id":"27824c0b-5b36-4147-ac7b-bd8c6a95ac5c","year":null},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.925778Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:b274f8b970bf7e67bd64bfeb39f921a65e3b8513d518ec4fd1a7f5f49f0c6482","observation_id":"e8c0fc1a-6df0-49e0-b480-c2f30721ec82","resolution":{"observed_at":"2026-08-07T10:52:08.475732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.466553Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"b53136f8-7daf-411c-874a-5bf12b4e37e7","year":2021},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.928088Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:575a2233403f3d37c4596d6bb87244a4fc8605e182bcd352e0fd52c47926cffd","observation_id":"ced3fd0c-c446-4fe1-b2e7-1470a1106e49","resolution":{"observed_at":"2026-08-07T10:52:08.468986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.459813Z","title":"GIFD: A generative gradient inversion method with fea- ture domain optimization","venue":null,"work_id":"be36b777-07be-48c7-bab9-0be3d308a74f","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.930208Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:7ebe2b89b5f05dce3b3727d812b4d2801484232d815892ea59dd3dd5fdcfa33f","observation_id":"00d60324-a0d6-4c29-8b48-1f670dedd445","resolution":{"observed_at":"2026-08-07T10:52:08.462186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.451182Z","title":"Privacy backdoors: Stealing data with corrupted pretrained models","venue":null,"work_id":"4cee768a-3c8f-4954-b135-f34e357589a2","year":null},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.932531Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:33524eb8c6a27ff71a9a4a080e3df7ce26f536161c0bc78e2d150b4db20b23df","observation_id":"2e2615b1-e15d-4d15-a042-80dd5f10ceee","resolution":{"observed_at":"2026-08-07T10:52:08.455188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.443585Z","title":"Fowl, Jonas Geiping, Wojciech Czaja, Micah Gold- blum, and Tom Goldstein","venue":null,"work_id":"400828ab-6b3d-40f5-8308-c9ed8b7b6fcd","year":2022},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.934728Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:2fa857844e8fa5a707369b1b671fb6d8949fe3d88812c6044c7417ab7f19fb65","observation_id":"35cad2b0-8d47-4722-b274-c2815360f3ae","resolution":{"observed_at":"2026-08-07T10:52:08.445982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.436972Z","title":"Fowl, Jonas Geiping, Steven Reich, Yuxin Wen, Wojciech Czaja, Micah Goldblum, and Tom Goldstein","venue":null,"work_id":"f39bdb24-5d07-4542-bfff-00895831c133","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.937013Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:8fe26300d40c1ac8f5e7aee90a16c00a93ea4c7b63f59c053006a0611000fcf5","observation_id":"219cbc82-57b5-4cb3-9a42-80973b86e410","resolution":{"observed_at":"2026-08-07T10:52:08.439236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.430262Z","title":"Practical membership inference attacks against fine-tuned large language models via self- prompt calibration","venue":null,"work_id":"a26e41f5-614d-4e21-9d21-ec240857544c","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.939115Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:0b1f6cdb4900d43240270422851245be3894b4d821bf83e3f6ab4c98538e8e58","observation_id":"d4aa687c-f975-49a7-8656-87a8085e4406","resolution":{"observed_at":"2026-08-07T10:52:08.432619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.423558Z","title":"Inverting gradients - how easy is it to break privacy in federated learning? In Advances in Neural Infor- mation Processing Systems (NeurIPS), 2020","venue":null,"work_id":"370a9976-2034-4480-875e-59e629de0cd7","year":2020},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.941195Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:15e4aa8b9bb1e6df0447cf7948950b92184c5107fcab40b7883a9076db3de9fa","observation_id":"0af4447d-20fa-48c8-8754-6847306363ef","resolution":{"observed_at":"2026-08-07T10:52:08.425915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.417019Z","title":"Gradvit: Gradi- ent inversion of vision transformers","venue":null,"work_id":"45ac5bc8-7c53-4b26-bc9e-be470af42088","year":2022},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.943515Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:d09683a06b83717cb12b54cbb592f2c6bc6dcc4798a3f797a6a4c4d6799fb739","observation_id":"d119f9ea-cafa-4eb8-a651-75f9af46a5cf","resolution":{"observed_at":"2026-08-07T10:52:08.419316Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.410156Z","title":"Gaussian error linear units (gelus)","venue":null,"work_id":"8333cffc-486c-455b-a356-5cc1270de5a9","year":2016},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.945760Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:a135d79b96cb7278b5d3fefce166bae00f78ffe07c208e13ad58a2ba4422f2d2","observation_id":"fcc996b1-45d0-435b-91c1-b917fb77f002","resolution":{"observed_at":"2026-08-07T10:52:08.412559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.403579Z","title":"Parameter-efficient transfer learning for NLP","venue":null,"work_id":"87f56b6d-a549-432b-8bd2-d77e17ad663a","year":2019},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.948062Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:d585b918bf79d732c4a5cbeda80c3c110e41f683ba16cfa770521a8c6df7a981","observation_id":"6002673b-4e80-436e-a887-092479cbc4d5","resolution":{"observed_at":"2026-08-07T10:52:08.405871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.396959Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","venue":null,"work_id":"ad6c128f-286e-4faa-8ea6-52f5d8e5682a","year":2022},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.950144Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:54ddbeb28ca6f82a456e5fd72f8c0cea462c5569d14aeb6783ea14f499becc56","observation_id":"15395447-c54f-4137-b1e3-bee5443c0ff0","resolution":{"observed_at":"2026-08-07T10:52:08.399335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.390171Z","title":"Evaluating gradient inversion attacks and de- fenses in federated learning","venue":null,"work_id":"c0c6ea1c-3046-450f-a479-44698d8196db","year":2021},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.952170Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:37c0ea0009f57f52fdeb0159c8ea89fceef4ffd2f05088b0e5763106fe5153cf","observation_id":"d95480e3-1720-4943-bbd1-0a9d174441df","resolution":{"observed_at":"2026-08-07T10:52:08.392428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.383598Z","title":"Gradient inversion with generative image prior","venue":null,"work_id":"8b31f89e-fef9-43c5-8d72-6d75218243f7","year":2021},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.954393Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:ce43366bacd4bf97db1fb9c2541f44b23a6cfddfb3bc7dc2d2a781eb167b8c69","observation_id":"8e2b9b01-b171-44c1-912f-603468a7b755","resolution":{"observed_at":"2026-08-07T10:52:08.385792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.377242Z","title":"Belongie, Bharath Hariharan, and Ser-Nam Lim","venue":null,"work_id":"e70c1f62-8cb9-4d4c-8e20-0a2534b58025","year":2022},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.956633Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:75f5ca61218d18686e752436389020bc42d6e1e5231e1cb512037e772b8e034c","observation_id":"178fc1d6-f0cc-4df4-931b-fafe41bca7ed","resolution":{"observed_at":"2026-08-07T10:52:08.379296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.370502Z","title":"Edward Suh, Moinuddin K","venue":null,"work_id":"9f7f473f-a872-47e7-b2f7-f1168977999b","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.958612Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:0e8e9f692616710a897818b72930925543ab0834d95a807defb2464e1c10d741","observation_id":"d6eb02ef-2aa3-4c56-a776-ffe06d50bff1","resolution":{"observed_at":"2026-08-07T10:52:08.372648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.363903Z","title":"Client-customized adaptation for parameter-efficient federated learning","venue":null,"work_id":"23972e8c-6882-43d2-88ac-1ee18aad1f59","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.960836Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:5c7dbbe7108608315bd4b218119aa35a3168b32f8c02bd9f47f536fbbcb82999","observation_id":"e7de4cd1-6a98-41ee-92be-09f19a536f77","resolution":{"observed_at":"2026-08-07T10:52:08.366273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.357297Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"4b8bc290-5577-4046-99b6-384fc25b8161","year":2009},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.962930Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:be66e524d328edbe1984e7e9b2a2135cf9f2c5998d58cc516a2679355ea5ba81","observation_id":"f529f671-d475-401d-a8f9-a68c9282bf42","resolution":{"observed_at":"2026-08-07T10:52:08.359621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.350884Z","title":"Tiny imagenet visual recognition challenge","venue":null,"work_id":"55c4b7ec-8251-4e04-82c3-45743bfdc77b","year":2015},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.964965Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:d26a5ab6163e827bf8c9b43e5426847a88ae6bca81792375ca4fe129792b9f66","observation_id":"7006b5ad-7348-4dac-b009-19b28f757692","resolution":{"observed_at":"2026-08-07T10:52:08.353067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.344270Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":"fae2b49b-f535-4581-bc79-54d42392428b","year":2021},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.966993Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:61b247751e6fcbd869c2c1fdf0a9e082e79766098073bb316e341553f916a4e8","observation_id":"c26c74b4-1514-42ca-9790-701eab266702","resolution":{"observed_at":"2026-08-07T10:52:08.346534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.337566Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":"59e46690-8bba-4831-b96c-62def744dd1a","year":2021},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.969129Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:1536483223a2defe337fe5352c118933f0c197a4a8318226c9fcd9edee88527c","observation_id":"408b35de-e095-4106-8d72-ab0006860a03","resolution":{"observed_at":"2026-08-07T10:52:08.339824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.330929Z","title":"Au- diting privacy defenses in federated learning via generative gradient leakage","venue":null,"work_id":"114ec083-56f0-44cb-a7b7-590d35926a0e","year":2022},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.971170Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:0c39cec3c853fa0a5a0343564299645bb6001a8a6a62a412c835b35074c431dd","observation_id":"f3000e97-37a2-4ed8-aca2-200f66762dfa","resolution":{"observed_at":"2026-08-07T10:52:08.333287Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.324395Z","title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","venue":null,"work_id":"23cf53cc-baf7-4373-b8cc-d0619d5a88a6","year":2018},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.973138Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:736d9087d6fb3b0c64c804b8b0cc7c56ed9d9867552a9904e0719fd185074e59","observation_id":"c1a2c2b1-1d17-4c6c-bf3a-54202a2b5063","resolution":{"observed_at":"2026-08-07T10:52:08.326706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.317690Z","title":"Pre- curious: How innocent pre-trained language models turn into privacy traps","venue":null,"work_id":"e181779a-f1e5-461b-9874-c3c2ab51ee6a","year":2024},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.975156Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:43933778e222e207da97436f3be3aed39d9ffec2b486ac7d9ce039d708ab6ae6","observation_id":"07bb609f-a879-439b-97ba-aede2daac737","resolution":{"observed_at":"2026-08-07T10:52:08.319986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.311077Z","title":"APRIL: finding the achilles’ heel on privacy for vision transformers","venue":null,"work_id":"d3ac8d1c-b282-457d-9a9a-42624a377ea7","year":2022},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.977562Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:e56957777929a2c8bdc63139707e23121bb5957a8076eee4cd9bdea83feca12f","observation_id":"c661ec25-074c-4600-9c5b-ec7f8de42863","resolution":{"observed_at":"2026-08-07T10:52:08.313426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.304359Z","title":"Analyzing leak- age of personally identifiable information in language mod- els","venue":null,"work_id":"7b1754da-776d-4705-8f07-bcaead06f547","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.979809Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:6f2ebb80bf966f5a86151ca37868648bab3ebaaad0bd5bdec3f2e80ad3104e91","observation_id":"7cc5817b-e555-4598-bde8-0c6d09188be1","resolution":{"observed_at":"2026-08-07T10:52:08.306776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.297413Z","title":"Re- ducing communication overhead in federated learning for pre-trained language models using parameter-efficient fine- tuning","venue":null,"work_id":"26409583-4db3-413f-aa0a-1735a9986f29","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.981939Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:b577de5db9295a837530f41a4c37d81846718998fc8ca41a81e00432dc77fb31","observation_id":"d7f0bfc4-aba1-4c21-aa93-436b2ec40c70","resolution":{"observed_at":"2026-08-07T10:52:08.299944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.290434Z","title":"Mini but mighty: Finetuning vits with mini adapters","venue":null,"work_id":"1a47ac58-1503-4bde-8279-865233344f59","year":2024},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.983998Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:20fc78249dd18e81950d113b17c0aaa627e9ebffca539c8734ffb30902f6a42e","observation_id":"02fd6425-c1f9-4f24-8fa5-672073d0d7ed","resolution":{"observed_at":"2026-08-07T10:52:08.292816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.283485Z","title":"Communication- efficient learning of deep networks from decentralized data","venue":null,"work_id":"169a7876-6d50-4364-8a42-a0d735f94f14","year":2017},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.986176Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:6b414ff49132c8ff010d5481da42d948a8c33ac5a4a37b846a49660f565c04cb","observation_id":"690ea2c3-755f-43bd-8bd7-79daa54d5871","resolution":{"observed_at":"2026-08-07T10:52:08.285871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.276828Z","title":"Shokri, and Amir Houmansadr","venue":null,"work_id":"368360db-74c8-4d7f-9975-5eaeaa894fd2","year":2019},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.988257Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:9806c71c4d28724bac2c2cf7e60e7ec07a918bde04c7ca4026269a457ed87519","observation_id":"255e54ba-3146-4ff6-9689-7a698c817e35","resolution":{"observed_at":"2026-08-07T10:52:08.279035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.270252Z","title":null,"venue":null,"work_id":"d925179f-f14d-476c-b0be-66635c15bd5a","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.990538Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:62dbc6915174ea7ee4b0442e8132644b75db61b8c8dc56742248b100d30dfa7c","observation_id":"9b0ede9b-b5a6-4ec5-93d5-0439cf30750a","resolution":{"observed_at":"2026-08-07T10:52:08.272547Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.263575Z","title":null,"venue":null,"work_id":"d4614aee-0c68-4bec-b1fd-5eb87aa6533b","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.992757Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:687d4fc5b1c2b97b23a0502b3594b5c019144423c29217938e0fc558e5692c56","observation_id":"d07be10b-c399-4b37-979d-066524e23116","resolution":{"observed_at":"2026-08-07T10:52:08.265749Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.256827Z","title":"Eluding secure aggregation in federated learning via model inconsistency","venue":null,"work_id":"6ae081df-faa7-428e-a9e2-5fa10cfeba49","year":2022},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.994969Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:597d6b600d2c249bd1a0b91dd0bbcdd16d1dcc7e724aaa5b15d3a1c52f601a5f","observation_id":"703047d5-3b2e-414e-b5ce-c05dff38e21b","resolution":{"observed_at":"2026-08-07T10:52:08.259162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.249861Z","title":"Adapterhub: A framework for adapting transformers","venue":null,"work_id":"4d38f231-3d1b-40bc-bb2d-6eb4595016bc","year":2020},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.997463Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:aa2d0ef9249ec19cc418c21c9a8c519d9afa1f827a83e9c768b16c276390e228","observation_id":"f9db09f9-fec7-4c37-8f06-fb3697b6f19b","resolution":{"observed_at":"2026-08-07T10:52:08.252377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.243162Z","title":null,"venue":null,"work_id":"e50b31c4-0706-484c-9fea-77f2321deefb","year":2022},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:07.999906Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:3fced263b104213cc4b8bcb662e58fb04abcbece54ddf3a6732c841f9bb9be2b","observation_id":"ca5b032f-a6e9-4e68-81fe-612f0015c6ce","resolution":{"observed_at":"2026-08-07T10:52:08.245537Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.236525Z","title":"Dropout is NOT all you need to prevent gradient leakage","venue":null,"work_id":"ea49a1ac-e66f-45c3-adeb-8d41e0a11270","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.002169Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:ecd4ff12ef59c4c3910d69eabb1ce41b117b908c1bbeb03815edaf315de648ea","observation_id":"bf233fbf-95ae-4ce6-96b5-d5cf349c384f","resolution":{"observed_at":"2026-08-07T10:52:08.238837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.229777Z","title":"Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov","venue":null,"work_id":"fa1e1eaf-a720-4a79-99d9-cb8bb60b5e15","year":2017},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.004412Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:7306e1a1dd1a735404efe4c0c7368a740a295a8fdcb4f2e6c3db2bfca15c85fd","observation_id":"f41e7b93-65a3-4e67-abb9-ef5cd61f513c","resolution":{"observed_at":"2026-08-07T10:52:08.232065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.223032Z","title":null,"venue":null,"work_id":"80106579-8685-449f-b101-3ebc6ffc8d80","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.006714Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:4aea6d9c41d6e4e2c68b096b90b6250285b3f027436dce100dc7026625eb5236","observation_id":"ec93c9f3-8e1c-4bf6-80a1-e42b62dd6adc","resolution":{"observed_at":"2026-08-07T10:52:08.225301Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.216371Z","title":"Systematic evaluation of pri- vacy risks of machine learning models","venue":null,"work_id":"880ee3a9-f1f9-4178-837d-d94348b1644e","year":null},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.009046Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:65e378bd0bf245c33204c63ed52af0093cb8f12af13516ec2c464ca465635ea9","observation_id":"e9b4237b-ce64-49b8-be85-a5a8ada57588","resolution":{"observed_at":"2026-08-07T10:52:08.218784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.209668Z","title":"Im- proving lora in privacy-preserving federated learning","venue":null,"work_id":"d712a94c-6895-4c95-97ad-6c396c6e7663","year":2024},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.011540Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:87b2302b6f16c4c4dff378cfb19eef15362915bf5901a10c187c80d921b691c1","observation_id":"9f4f00a3-6816-4c7d-bb37-27ac323dee95","resolution":{"observed_at":"2026-08-07T10:52:08.211917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.203196Z","title":"VL- ADAPTER: parameter-efficient transfer learning for vision- and-language tasks","venue":null,"work_id":"d362838f-8224-4e0c-906f-dfe2905aadd9","year":null},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.013709Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:0c32c2ded8125d1251588cf83564af334ac1b07e6cf352b17b0710c66d4cdb8b","observation_id":"99e1c1d8-6b65-48d3-be0b-545990a72a97","resolution":{"observed_at":"2026-08-07T10:52:08.205552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.195780Z","title":"Manipulating transfer learning for property inference","venue":null,"work_id":"9f211d79-88b5-43f1-9dd1-ee1686d542a0","year":null},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.016126Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:b8409a2eadec8f4aa7cc1ec241a048a688616531a5f082dd93cfe9d07865853c","observation_id":"a84cbbf1-96ed-46b1-ab21-19b43364ca0e","resolution":{"observed_at":"2026-08-07T10:52:08.198710Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.189187Z","title":"Vu, Truc D","venue":null,"work_id":"e4eeb2d2-5851-429f-b42d-0515744c2967","year":2024},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.018537Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:c603265dbbf7091acb331a993c136e57792bf8ac574eedc567c38ed9d698f5d3","observation_id":"cf6c7000-cb58-4d49-8df8-b1eda35f34b7","resolution":{"observed_at":"2026-08-07T10:52:08.191359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.182310Z","title":"Sheikh, and Eero P","venue":null,"work_id":"9a1830bd-f55c-445e-b6f6-341b0e18cd61","year":2004},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.020998Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:a38145f0c87669cdbed65761b853a69f28c1fa13e96db76f0920384870ba1da4","observation_id":"d8a34e54-adab-49fa-8a46-081a5f54c421","resolution":{"observed_at":"2026-08-07T10:52:08.184733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.174942Z","title":"Pretrained models for multilingual federated learning","venue":null,"work_id":"f80c54c3-f1be-4a08-912a-da55b118ac9a","year":2022},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.023120Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:6669bb30abe814d45f0bd5dc3779e9ca0769bd8f7de514011422a0e6e28d837c","observation_id":"5aa2ef3b-c25c-49b2-801a-d7a78afc8666","resolution":{"observed_at":"2026-08-07T10:52:08.177394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.168024Z","title":"Batched low-rank adap- tation of foundation models","venue":null,"work_id":"46a36249-83b2-45e0-8500-ab8487e24355","year":2024},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.025480Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:cdad8b1c51e2b4b122ae76bee4bd6ded2ae773ee0136b6de50fc0e25d8228505","observation_id":"f248e0cf-5249-4b94-9e13-631f7a3b6ebc","resolution":{"observed_at":"2026-08-07T10:52:08.170421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.160853Z","title":"Fishing for user data in large-batch fed- erated learning via gradient magnification","venue":null,"work_id":"ebe21016-a21d-45da-91ec-75b2e3ddb0aa","year":2022},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.027885Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:8bdd754d23c2aa23fa65e836a49856999eb2d48af13df5e674e07baefaf50f43","observation_id":"eab3b880-e76c-430e-9af6-dd92e8f7ac9e","resolution":{"observed_at":"2026-08-07T10:52:08.163516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.153824Z","title":"Privacy back- doors: Enhancing membership inference through poisoning pre-trained models","venue":null,"work_id":"9928a3ea-91a0-414c-a446-33272cd7d8db","year":2024},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.030022Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:1c817a8f5041f5d242abc168942c4a105a43dde8f4a852acddc5bc071f57da21","observation_id":"829664a6-c58f-4a1f-9b7b-f3b834d36580","resolution":{"observed_at":"2026-08-07T10:52:08.156260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.146565Z","title":"Perada: Parameter-efficient federated learning personalization with generalization guarantees","venue":null,"work_id":"4e29b7ed-29bc-4412-8c40-c67d2dcab55a","year":2024},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.032432Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:bb471eb2a4e2c38a460603143c828fc0dcc439ebff33ff023272ebc1215151f1","observation_id":"cd43c059-8913-488b-8580-8b161fb9729e","resolution":{"observed_at":"2026-08-07T10:52:08.149039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.139050Z","title":"Efficient low-rank backprop- agation for vision transformer adaptation","venue":null,"work_id":"c09985c5-7ed5-47a2-a5d3-2130dad1eb58","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.034783Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:10b9747f26fef222924083c19294315d6218eb88b595d97203ce3ced8501f924","observation_id":"5e3cdb84-ac07-438c-a339-8778c5ad03ca","resolution":{"observed_at":"2026-08-07T10:52:08.141732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.131740Z","title":null,"venue":null,"work_id":"98139e3d-9ef8-405a-bf28-e3f9817c4dbf","year":2021},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.037218Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:ea46e48902bb8d073d181ae03008ff7cd97d42f739ad400fa1c585bc69360539","observation_id":"4538e37d-b569-40de-970b-3d8498b0fecd","resolution":{"observed_at":"2026-08-07T10:52:08.134066Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.124114Z","title":"How does a deep learning model architecture impact its privacy? A comprehensive study of privacy attacks on cnns and transformers","venue":null,"work_id":"538d4e5b-4c82-477b-b704-736b043da1d8","year":2024},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.039716Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:c8047bbc24b0ae24c921f364bdb3c4533256dae2bb38054c89f48e9b3df23dd8","observation_id":"554f6bfe-28c4-444b-81e5-7fef685324ac","resolution":{"observed_at":"2026-08-07T10:52:08.126886Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.115567Z","title":"Efros, Eli Shecht- man, and Oliver Wang","venue":null,"work_id":"a8533471-2bb7-4eff-b7a8-590ddbec6a9e","year":2018},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.042291Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:a9e30369d00dc8f5d657288a5b6efc8e8007fbbc1a4ab0ac9e88226d2830bcab","observation_id":"3aaa7e5d-d2cc-448e-9e5c-a1853442ec8c","resolution":{"observed_at":"2026-08-07T10:52:08.118327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.107607Z","title":"Roy-Chowdhury, Ananda Theertha Suresh, and Samet Oymak","venue":null,"work_id":"7be3f494-40a5-4d6c-9d99-a07ff5416808","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.044513Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:ed196913a928fa4f4f1c0fe45ae9b7275934bcc6d4727060efe68256fe0e288d","observation_id":"f708e7ad-33e9-4d27-81bd-4be78cfffaf4","resolution":{"observed_at":"2026-08-07T10:52:08.110157Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.099506Z","title":"Fedpetuning: When fed- erated learning meets the parameter-efficient tuning methods of pre-trained language models","venue":null,"work_id":"7e5ba18b-3ff2-41fe-80f4-53bf37580d6f","year":null},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.046736Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:77f123162cf5efe7c60459bd0f0d4c9c94443d6d23d3381a016088dd22dcf12b","observation_id":"b8e665a6-0b90-4e3c-9e30-8f64e0741180","resolution":{"observed_at":"2026-08-07T10:52:08.102579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.091814Z","title":null,"venue":null,"work_id":"74b0bf47-df03-4909-b908-079fed1c805c","year":2024},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.049961Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:3094ebf232d8f8fbcc0f719189c5962d3f4882862366b6e86761fc9028e3a386","observation_id":"2cb89e28-8369-4d6a-85cb-87b2dfa52604","resolution":{"observed_at":"2026-08-07T10:52:08.094275Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.083771Z","title":"Zhao, Ahmed Roushdy Elkordy, Atul Sharma, Yahya H","venue":null,"work_id":"9e0c89ec-8367-4ee1-9d26-e5bcbe8bb195","year":2023},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.052421Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:34546789c5700dfbc2b6d0a4250c7f1d429910f3ed6af3238f5b4c37df8c05f4","observation_id":"ab97b445-4f68-4f86-a305-c3467b3bad30","resolution":{"observed_at":"2026-08-07T10:52:08.086729Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:08.074786Z","title":"Deep leakage from gradients","venue":null,"work_id":"2d29fc16-ca77-4e9b-a655-4e917af95462","year":2019},"citing_paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:08.054810Z"},"links":{"citing_paper":"/paper/2506.04453"},"observation_digest":"sha256:ae67d2a5ef02990cf303afd947b861c188756bde1acf3b6082cc3807d3363d67","observation_id":"242b6e45-58c5-4ce8-aa48-e3632bb7b312","resolution":{"observed_at":"2026-08-07T10:52:08.078215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.04453","last_updated":"2025-06-04T21:14:21Z","latest_version":1,"primary_category":"eess.IV","snapshot_observed_at":"2026-08-07T10:39:34.176545Z","submitted_at":"2025-06-04T21:14:21Z","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning"},"reference_resolution":{"displayed":70,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":0,"verified_fuzzy":63},"total_outbound_references":70},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 70 of 70 outbound references and 0 inbound Pith citation observations for arXiv:2506.04453."}