{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BDDIYMOZRUWNLFKVF56NBAXRRI","short_pith_number":"pith:BDDIYMOZ","schema_version":"1.0","canonical_sha256":"08c68c31d98d2cd595552f7cd082f18a3eee5048c8ddeacf0429ef3bf56d39f3","source":{"kind":"arxiv","id":"2203.00915","version":1},"attestation_state":"computed","paper":{"title":"MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Members","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Birhanu Eshete, Ismat Jarin","submitted_at":"2022-03-02T07:53:21Z","abstract_excerpt":"In membership inference attacks (MIAs), an adversary observes the predictions of a model to determine whether a sample is part of the model's training data. Existing MIA defenses conceal the presence of a target sample through strong regularization, knowledge distillation, confidence masking, or differential privacy.\n  We propose MIAShield, a new MIA defense based on preemptive exclusion of member samples instead of masking the presence of a member. The key insight in MIAShield is weakening the strong membership signal that stems from the presence of a target sample by preemptively excluding i"},"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":"2203.00915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2022-03-02T07:53:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e743ae8f433e0ea9497884fc687a0e51eff1dd01fd4cd71d6fc3f06f25c571c2","abstract_canon_sha256":"e620d14c9cd732ea5acd3cae213c89fbd86bd064394a978eca26eeeea61228cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:35.313793Z","signature_b64":"mYr8gxyogLWWFReC2ObMTL3qJjB+Qt6i25oBDkobs3JeKEqedotgZy8N9sgc0YfCQTezsotvzjlxRztgtJhHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08c68c31d98d2cd595552f7cd082f18a3eee5048c8ddeacf0429ef3bf56d39f3","last_reissued_at":"2026-07-05T04:01:35.313373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:35.313373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Members","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Birhanu Eshete, Ismat Jarin","submitted_at":"2022-03-02T07:53:21Z","abstract_excerpt":"In membership inference attacks (MIAs), an adversary observes the predictions of a model to determine whether a sample is part of the model's training data. Existing MIA defenses conceal the presence of a target sample through strong regularization, knowledge distillation, confidence masking, or differential privacy.\n  We propose MIAShield, a new MIA defense based on preemptive exclusion of member samples instead of masking the presence of a member. The key insight in MIAShield is weakening the strong membership signal that stems from the presence of a target sample by preemptively excluding i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00915","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/2203.00915/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":"2203.00915","created_at":"2026-07-05T04:01:35.313440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.00915v1","created_at":"2026-07-05T04:01:35.313440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00915","created_at":"2026-07-05T04:01:35.313440+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDDIYMOZRUWN","created_at":"2026-07-05T04:01:35.313440+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDDIYMOZRUWNLFKV","created_at":"2026-07-05T04:01:35.313440+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDDIYMOZ","created_at":"2026-07-05T04:01:35.313440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BDDIYMOZRUWNLFKVF56NBAXRRI","json":"https://pith.science/pith/BDDIYMOZRUWNLFKVF56NBAXRRI.json","graph_json":"https://pith.science/api/pith-number/BDDIYMOZRUWNLFKVF56NBAXRRI/graph.json","events_json":"https://pith.science/api/pith-number/BDDIYMOZRUWNLFKVF56NBAXRRI/events.json","paper":"https://pith.science/paper/BDDIYMOZ"},"agent_actions":{"view_html":"https://pith.science/pith/BDDIYMOZRUWNLFKVF56NBAXRRI","download_json":"https://pith.science/pith/BDDIYMOZRUWNLFKVF56NBAXRRI.json","view_paper":"https://pith.science/paper/BDDIYMOZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.00915&json=true","fetch_graph":"https://pith.science/api/pith-number/BDDIYMOZRUWNLFKVF56NBAXRRI/graph.json","fetch_events":"https://pith.science/api/pith-number/BDDIYMOZRUWNLFKVF56NBAXRRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDDIYMOZRUWNLFKVF56NBAXRRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDDIYMOZRUWNLFKVF56NBAXRRI/action/storage_attestation","attest_author":"https://pith.science/pith/BDDIYMOZRUWNLFKVF56NBAXRRI/action/author_attestation","sign_citation":"https://pith.science/pith/BDDIYMOZRUWNLFKVF56NBAXRRI/action/citation_signature","submit_replication":"https://pith.science/pith/BDDIYMOZRUWNLFKVF56NBAXRRI/action/replication_record"}},"created_at":"2026-07-05T04:01:35.313440+00:00","updated_at":"2026-07-05T04:01:35.313440+00:00"}