{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:P3B4TCLMUYUH27Y3X6P7C75JFE","short_pith_number":"pith:P3B4TCLM","schema_version":"1.0","canonical_sha256":"7ec3c9896ca6287d7f1bbf9ff17fa92936748bd353e9b67831dad8fe67016cb8","source":{"kind":"arxiv","id":"2106.11384","version":1},"attestation_state":"computed","paper":{"title":"Membership Inference on Word Embedding and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Esha Ghosh, Huseyin A. Inan, Marcello Hasegawa, Melissa Chase, Saeed Mahloujifar","submitted_at":"2021-06-21T19:37:06Z","abstract_excerpt":"In the text processing context, most ML models are built on word embeddings. These embeddings are themselves trained on some datasets, potentially containing sensitive data. In some cases this training is done independently, in other cases, it occurs as part of training a larger, task-specific model. In either case, it is of interest to consider membership inference attacks based on the embedding layer as a way of understanding sensitive information leakage. But, somewhat surprisingly, membership inference attacks on word embeddings and their effect in other natural language processing (NLP) t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.11384","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-21T19:37:06Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"2841ad512b13024d5dcffebf26773fbe38b0ed10976743d6e1020d70bf419cf7","abstract_canon_sha256":"feb59edf7abe59b76efe384137d95b388e020b63cfb8986195c3a31537f95ff6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:28.773448Z","signature_b64":"+VM6i+yDmq1/tw1qOvb+CeqDOEYftgiAGsZtNK93QLKEIalIEVMWlspiUVveBl/gP0HMXk+74NlVvIHB14pLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ec3c9896ca6287d7f1bbf9ff17fa92936748bd353e9b67831dad8fe67016cb8","last_reissued_at":"2026-07-05T02:51:28.773059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:28.773059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Membership Inference on Word Embedding and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Esha Ghosh, Huseyin A. Inan, Marcello Hasegawa, Melissa Chase, Saeed Mahloujifar","submitted_at":"2021-06-21T19:37:06Z","abstract_excerpt":"In the text processing context, most ML models are built on word embeddings. These embeddings are themselves trained on some datasets, potentially containing sensitive data. In some cases this training is done independently, in other cases, it occurs as part of training a larger, task-specific model. In either case, it is of interest to consider membership inference attacks based on the embedding layer as a way of understanding sensitive information leakage. But, somewhat surprisingly, membership inference attacks on word embeddings and their effect in other natural language processing (NLP) t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11384","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/2106.11384/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.11384","created_at":"2026-07-05T02:51:28.773127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.11384v1","created_at":"2026-07-05T02:51:28.773127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11384","created_at":"2026-07-05T02:51:28.773127+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3B4TCLMUYUH","created_at":"2026-07-05T02:51:28.773127+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3B4TCLMUYUH27Y3","created_at":"2026-07-05T02:51:28.773127+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3B4TCLM","created_at":"2026-07-05T02:51:28.773127+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17341","citing_title":"Single-Sample Black-Box Membership Inference Attack against Vision-Language Models via Cross-modal Semantic Alignment","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2310.16789","citing_title":"Detecting Pretraining Data from Large Language Models","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3B4TCLMUYUH27Y3X6P7C75JFE","json":"https://pith.science/pith/P3B4TCLMUYUH27Y3X6P7C75JFE.json","graph_json":"https://pith.science/api/pith-number/P3B4TCLMUYUH27Y3X6P7C75JFE/graph.json","events_json":"https://pith.science/api/pith-number/P3B4TCLMUYUH27Y3X6P7C75JFE/events.json","paper":"https://pith.science/paper/P3B4TCLM"},"agent_actions":{"view_html":"https://pith.science/pith/P3B4TCLMUYUH27Y3X6P7C75JFE","download_json":"https://pith.science/pith/P3B4TCLMUYUH27Y3X6P7C75JFE.json","view_paper":"https://pith.science/paper/P3B4TCLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.11384&json=true","fetch_graph":"https://pith.science/api/pith-number/P3B4TCLMUYUH27Y3X6P7C75JFE/graph.json","fetch_events":"https://pith.science/api/pith-number/P3B4TCLMUYUH27Y3X6P7C75JFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3B4TCLMUYUH27Y3X6P7C75JFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3B4TCLMUYUH27Y3X6P7C75JFE/action/storage_attestation","attest_author":"https://pith.science/pith/P3B4TCLMUYUH27Y3X6P7C75JFE/action/author_attestation","sign_citation":"https://pith.science/pith/P3B4TCLMUYUH27Y3X6P7C75JFE/action/citation_signature","submit_replication":"https://pith.science/pith/P3B4TCLMUYUH27Y3X6P7C75JFE/action/replication_record"}},"created_at":"2026-07-05T02:51:28.773127+00:00","updated_at":"2026-07-05T02:51:28.773127+00:00"}