{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6TKQO4FBQVXEUPDVI3GZKQCDLV","short_pith_number":"pith:6TKQO4FB","canonical_record":{"source":{"id":"2605.18762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-10T08:26:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84b62af56bdd3e9013de3212d906644631c95d7f9b922f46cfe5721362e6a7be","abstract_canon_sha256":"3b122deeb0c2b9089b2037e0fec24da8b08d23604189605b483c7cf0028f381a"},"schema_version":"1.0"},"canonical_sha256":"f4d50770a1856e4a3c7546cd9540435d68399a2f5451cd24bf54faf09a468fb7","source":{"kind":"arxiv","id":"2605.18762","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18762","created_at":"2026-05-20T00:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18762v1","created_at":"2026-05-20T00:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18762","created_at":"2026-05-20T00:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"6TKQO4FBQVXE","created_at":"2026-05-20T00:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"6TKQO4FBQVXEUPDV","created_at":"2026-05-20T00:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"6TKQO4FB","created_at":"2026-05-20T00:06:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6TKQO4FBQVXEUPDVI3GZKQCDLV","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-10T08:26:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84b62af56bdd3e9013de3212d906644631c95d7f9b922f46cfe5721362e6a7be","abstract_canon_sha256":"3b122deeb0c2b9089b2037e0fec24da8b08d23604189605b483c7cf0028f381a"},"schema_version":"1.0"},"canonical_sha256":"f4d50770a1856e4a3c7546cd9540435d68399a2f5451cd24bf54faf09a468fb7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:20.581104Z","signature_b64":"8IlPVZbU/InkqcgK1dQ7oGcPietEH2oDQB+wJXqD9sahb30RAFI+FzuNinHhnLI7FCUHYDB+wsqnqUJ79DjtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4d50770a1856e4a3c7546cd9540435d68399a2f5451cd24bf54faf09a468fb7","last_reissued_at":"2026-05-20T00:06:20.579141Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:20.579141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18762","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WB6srh5xgttCv0g1WdRe2J8vhMSDv5Y4PI2dNlTqA/i1gEVd6J1KaO1Je7NbYMtszI55UOQ+R4N2yiDpr5JDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T04:07:34.010891Z"},"content_sha256":"0a3a86eb0d5578b26faad1cb8f6383306ed50e76df6b309c0cca2ff5e58f132a","schema_version":"1.0","event_id":"sha256:0a3a86eb0d5578b26faad1cb8f6383306ed50e76df6b309c0cca2ff5e58f132a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6TKQO4FBQVXEUPDVI3GZKQCDLV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Danjue Chen, Jianfeng He, Ning Wang, Shixiong Li, Tao Li, Xingyu Lyu, Yidan Hu, Yimin Chen","submitted_at":"2026-04-10T08:26:40Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is widely used to augment large language models with external knowledge retrieval to improve reliability and generalization. However, recent studies have shown that RAG systems remain vulnerable to data extraction attacks, where adversaries can extract private data by embedding malicious commands into user queries. Despite their feasibility, existing attacks typically suffer from low data extraction rates and limited practical effectiveness. Here, we propose ALDEN, a novel attack that effectively and efficiently extracts private data from RAGs. First, we em"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18762","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.18762/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s4ukkDycnJ7abwDXiHnLv6TMdtI4K9f39ZQNMjhXnFu6V4my75ehTxf5adzl9eRsXhuX1ycSEzUwUsnh27P+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T04:07:34.011622Z"},"content_sha256":"07d9906318647c241097461f8f6bc2c682c585f80fdd0be435f41c02137bfef3","schema_version":"1.0","event_id":"sha256:07d9906318647c241097461f8f6bc2c682c585f80fdd0be435f41c02137bfef3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TKQO4FBQVXEUPDVI3GZKQCDLV/bundle.json","state_url":"https://pith.science/pith/6TKQO4FBQVXEUPDVI3GZKQCDLV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TKQO4FBQVXEUPDVI3GZKQCDLV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T04:07:34Z","links":{"resolver":"https://pith.science/pith/6TKQO4FBQVXEUPDVI3GZKQCDLV","bundle":"https://pith.science/pith/6TKQO4FBQVXEUPDVI3GZKQCDLV/bundle.json","state":"https://pith.science/pith/6TKQO4FBQVXEUPDVI3GZKQCDLV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TKQO4FBQVXEUPDVI3GZKQCDLV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6TKQO4FBQVXEUPDVI3GZKQCDLV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3b122deeb0c2b9089b2037e0fec24da8b08d23604189605b483c7cf0028f381a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-10T08:26:40Z","title_canon_sha256":"84b62af56bdd3e9013de3212d906644631c95d7f9b922f46cfe5721362e6a7be"},"schema_version":"1.0","source":{"id":"2605.18762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18762","created_at":"2026-05-20T00:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18762v1","created_at":"2026-05-20T00:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18762","created_at":"2026-05-20T00:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"6TKQO4FBQVXE","created_at":"2026-05-20T00:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"6TKQO4FBQVXEUPDV","created_at":"2026-05-20T00:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"6TKQO4FB","created_at":"2026-05-20T00:06:20Z"}],"graph_snapshots":[{"event_id":"sha256:07d9906318647c241097461f8f6bc2c682c585f80fdd0be435f41c02137bfef3","target":"graph","created_at":"2026-05-20T00:06:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.18762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) is widely used to augment large language models with external knowledge retrieval to improve reliability and generalization. However, recent studies have shown that RAG systems remain vulnerable to data extraction attacks, where adversaries can extract private data by embedding malicious commands into user queries. Despite their feasibility, existing attacks typically suffer from low data extraction rates and limited practical effectiveness. Here, we propose ALDEN, a novel attack that effectively and efficiently extracts private data from RAGs. First, we em","authors_text":"Danjue Chen, Jianfeng He, Ning Wang, Shixiong Li, Tao Li, Xingyu Lyu, Yidan Hu, Yimin Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-10T08:26:40Z","title":"ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18762","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0a3a86eb0d5578b26faad1cb8f6383306ed50e76df6b309c0cca2ff5e58f132a","target":"record","created_at":"2026-05-20T00:06:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3b122deeb0c2b9089b2037e0fec24da8b08d23604189605b483c7cf0028f381a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-10T08:26:40Z","title_canon_sha256":"84b62af56bdd3e9013de3212d906644631c95d7f9b922f46cfe5721362e6a7be"},"schema_version":"1.0","source":{"id":"2605.18762","kind":"arxiv","version":1}},"canonical_sha256":"f4d50770a1856e4a3c7546cd9540435d68399a2f5451cd24bf54faf09a468fb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4d50770a1856e4a3c7546cd9540435d68399a2f5451cd24bf54faf09a468fb7","first_computed_at":"2026-05-20T00:06:20.579141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:20.579141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8IlPVZbU/InkqcgK1dQ7oGcPietEH2oDQB+wJXqD9sahb30RAFI+FzuNinHhnLI7FCUHYDB+wsqnqUJ79DjtAg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:20.581104Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a3a86eb0d5578b26faad1cb8f6383306ed50e76df6b309c0cca2ff5e58f132a","sha256:07d9906318647c241097461f8f6bc2c682c585f80fdd0be435f41c02137bfef3"],"state_sha256":"4e75cb5dbdd5fc84be3397ea78c97d6a2ad811a182e140db7f48c541b5252e1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kIuj73/tB3xDhGptvJRZ6aOTpFWghs5Ykr8z1SflADfoj1Ap33kWPNoQwdhjhnMm4ig05/K7Jq3dWaSr/MXvBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T04:07:34.015044Z","bundle_sha256":"3d5f0e9feac82fe1aca7db69099b3f950d09ec0cbb52a3cd7d780b508eaba077"}}