{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LJQPXA7OP2S3GPMNEGUAB7U2QE","short_pith_number":"pith:LJQPXA7O","schema_version":"1.0","canonical_sha256":"5a60fb83ee7ea5b33d8d21a800fe9a8108be58b9a578ec1288beba4a012dc3a8","source":{"kind":"arxiv","id":"2210.11049","version":3},"attestation_state":"computed","paper":{"title":"How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Bo Liu, Guangsheng Zhang, Huan Tian, Ming Ding, Tianqing Zhu, Wanlei Zhou","submitted_at":"2022-10-20T06:44:37Z","abstract_excerpt":"As a booming research area in the past decade, deep learning technologies have been driven by big data collected and processed on an unprecedented scale. However, privacy concerns arise due to the potential leakage of sensitive information from the training data. Recent research has revealed that deep learning models are vulnerable to various privacy attacks, including membership inference attacks, attribute inference attacks, and gradient inversion attacks. Notably, the efficacy of these attacks varies from model to model. In this paper, we answer a fundamental question: Does model architectu"},"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":"2210.11049","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2022-10-20T06:44:37Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"93b7a4331d916bd82259e1e9dd0d2823a95af048ad3f7d64b2fbc787d044f3ec","abstract_canon_sha256":"eed1fb7051b8615db8e0ce52ca40df363f3c7b110c02225833365417953f4114"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:19.978653Z","signature_b64":"6DrSeLw9bKk8Qn7EVXBN2i4uB88cILuh6NoFfEv43Llkw/UdHQk/Y7W71DljAk5S2AuH4rO6ls/i+vbWbJrSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a60fb83ee7ea5b33d8d21a800fe9a8108be58b9a578ec1288beba4a012dc3a8","last_reissued_at":"2026-07-05T07:40:19.978218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:19.978218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Bo Liu, Guangsheng Zhang, Huan Tian, Ming Ding, Tianqing Zhu, Wanlei Zhou","submitted_at":"2022-10-20T06:44:37Z","abstract_excerpt":"As a booming research area in the past decade, deep learning technologies have been driven by big data collected and processed on an unprecedented scale. However, privacy concerns arise due to the potential leakage of sensitive information from the training data. Recent research has revealed that deep learning models are vulnerable to various privacy attacks, including membership inference attacks, attribute inference attacks, and gradient inversion attacks. Notably, the efficacy of these attacks varies from model to model. In this paper, we answer a fundamental question: Does model architectu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11049","kind":"arxiv","version":3},"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/2210.11049/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":"2210.11049","created_at":"2026-07-05T07:40:19.978273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.11049v3","created_at":"2026-07-05T07:40:19.978273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11049","created_at":"2026-07-05T07:40:19.978273+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJQPXA7OP2S3","created_at":"2026-07-05T07:40:19.978273+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJQPXA7OP2S3GPMN","created_at":"2026-07-05T07:40:19.978273+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJQPXA7O","created_at":"2026-07-05T07:40:19.978273+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/LJQPXA7OP2S3GPMNEGUAB7U2QE","json":"https://pith.science/pith/LJQPXA7OP2S3GPMNEGUAB7U2QE.json","graph_json":"https://pith.science/api/pith-number/LJQPXA7OP2S3GPMNEGUAB7U2QE/graph.json","events_json":"https://pith.science/api/pith-number/LJQPXA7OP2S3GPMNEGUAB7U2QE/events.json","paper":"https://pith.science/paper/LJQPXA7O"},"agent_actions":{"view_html":"https://pith.science/pith/LJQPXA7OP2S3GPMNEGUAB7U2QE","download_json":"https://pith.science/pith/LJQPXA7OP2S3GPMNEGUAB7U2QE.json","view_paper":"https://pith.science/paper/LJQPXA7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.11049&json=true","fetch_graph":"https://pith.science/api/pith-number/LJQPXA7OP2S3GPMNEGUAB7U2QE/graph.json","fetch_events":"https://pith.science/api/pith-number/LJQPXA7OP2S3GPMNEGUAB7U2QE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJQPXA7OP2S3GPMNEGUAB7U2QE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJQPXA7OP2S3GPMNEGUAB7U2QE/action/storage_attestation","attest_author":"https://pith.science/pith/LJQPXA7OP2S3GPMNEGUAB7U2QE/action/author_attestation","sign_citation":"https://pith.science/pith/LJQPXA7OP2S3GPMNEGUAB7U2QE/action/citation_signature","submit_replication":"https://pith.science/pith/LJQPXA7OP2S3GPMNEGUAB7U2QE/action/replication_record"}},"created_at":"2026-07-05T07:40:19.978273+00:00","updated_at":"2026-07-05T07:40:19.978273+00:00"}