{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:V4VL237TTTYDNNEDYDEN5NU3BJ","short_pith_number":"pith:V4VL237T","schema_version":"1.0","canonical_sha256":"af2abd6ff39cf036b483c0c8deb69b0a45a69281b474a8891b820bb7edb35bce","source":{"kind":"arxiv","id":"1904.05506","version":2},"attestation_state":"computed","paper":{"title":"Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kevin Duh, Matt Post, Sorami Hisamoto","submitted_at":"2019-04-11T02:53:21Z","abstract_excerpt":"Data privacy is an important issue for \"machine learning as a service\" providers. We focus on the problem of membership inference attacks: given a data sample and black-box access to a model's API, determine whether the sample existed in the model's training data. Our contribution is an investigation of this problem in the context of sequence-to-sequence models, which are important in applications such as machine translation and video captioning. We define the membership inference problem for sequence generation, provide an open dataset based on state-of-the-art machine translation models, and"},"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":"1904.05506","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-11T02:53:21Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"69f3586da5a9da4f3b913b80dea5ab130d2c7cac86b58d4513f0afce0f39bcac","abstract_canon_sha256":"d941494bae2b947c1279cbe194c023db47ec75ce163cf30f0dfb7d00b51ff2a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:47:56.714759Z","signature_b64":"fD77fte8Gmgxn/+PdBMd0FFg3P/Db3vFW3Ud0rJbXHir3pybaYoAYDdqkc2sJrs+Q4Y7lamnFdhuUPhVjaA6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af2abd6ff39cf036b483c0c8deb69b0a45a69281b474a8891b820bb7edb35bce","last_reissued_at":"2026-07-05T00:47:56.714285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:47:56.714285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kevin Duh, Matt Post, Sorami Hisamoto","submitted_at":"2019-04-11T02:53:21Z","abstract_excerpt":"Data privacy is an important issue for \"machine learning as a service\" providers. We focus on the problem of membership inference attacks: given a data sample and black-box access to a model's API, determine whether the sample existed in the model's training data. Our contribution is an investigation of this problem in the context of sequence-to-sequence models, which are important in applications such as machine translation and video captioning. We define the membership inference problem for sequence generation, provide an open dataset based on state-of-the-art machine translation models, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.05506","kind":"arxiv","version":2},"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/1904.05506/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":"1904.05506","created_at":"2026-07-05T00:47:56.714354+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.05506v2","created_at":"2026-07-05T00:47:56.714354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.05506","created_at":"2026-07-05T00:47:56.714354+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4VL237TTTYD","created_at":"2026-07-05T00:47:56.714354+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4VL237TTTYDNNED","created_at":"2026-07-05T00:47:56.714354+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4VL237T","created_at":"2026-07-05T00:47:56.714354+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.01454","citing_title":"V2S attack: building DNN-based voice conversion from automatic speaker verification","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V4VL237TTTYDNNEDYDEN5NU3BJ","json":"https://pith.science/pith/V4VL237TTTYDNNEDYDEN5NU3BJ.json","graph_json":"https://pith.science/api/pith-number/V4VL237TTTYDNNEDYDEN5NU3BJ/graph.json","events_json":"https://pith.science/api/pith-number/V4VL237TTTYDNNEDYDEN5NU3BJ/events.json","paper":"https://pith.science/paper/V4VL237T"},"agent_actions":{"view_html":"https://pith.science/pith/V4VL237TTTYDNNEDYDEN5NU3BJ","download_json":"https://pith.science/pith/V4VL237TTTYDNNEDYDEN5NU3BJ.json","view_paper":"https://pith.science/paper/V4VL237T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.05506&json=true","fetch_graph":"https://pith.science/api/pith-number/V4VL237TTTYDNNEDYDEN5NU3BJ/graph.json","fetch_events":"https://pith.science/api/pith-number/V4VL237TTTYDNNEDYDEN5NU3BJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4VL237TTTYDNNEDYDEN5NU3BJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4VL237TTTYDNNEDYDEN5NU3BJ/action/storage_attestation","attest_author":"https://pith.science/pith/V4VL237TTTYDNNEDYDEN5NU3BJ/action/author_attestation","sign_citation":"https://pith.science/pith/V4VL237TTTYDNNEDYDEN5NU3BJ/action/citation_signature","submit_replication":"https://pith.science/pith/V4VL237TTTYDNNEDYDEN5NU3BJ/action/replication_record"}},"created_at":"2026-07-05T00:47:56.714354+00:00","updated_at":"2026-07-05T00:47:56.714354+00:00"}