{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ST7W53SKZOVQCGHGSD66WFTLQJ","short_pith_number":"pith:ST7W53SK","schema_version":"1.0","canonical_sha256":"94ff6eee4acbab0118e690fdeb166b8278060fb6a81f5256dea84b9811549ab7","source":{"kind":"arxiv","id":"2011.14218","version":2},"attestation_state":"computed","paper":{"title":"FaceGuard: A Self-Supervised Defense Against Adversarial Face Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anil K. Jain, Debayan Deb, Xiaoming Liu","submitted_at":"2020-11-28T21:18:46Z","abstract_excerpt":"Prevailing defense mechanisms against adversarial face images tend to overfit to the adversarial perturbations in the training set and fail to generalize to unseen adversarial attacks. We propose a new self-supervised adversarial defense framework, namely FaceGuard, that can automatically detect, localize, and purify a wide variety of adversarial faces without utilizing pre-computed adversarial training samples. During training, FaceGuard automatically synthesizes challenging and diverse adversarial attacks, enabling a classifier to learn to distinguish them from real faces and a purifier atte"},"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":"2011.14218","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-28T21:18:46Z","cross_cats_sorted":[],"title_canon_sha256":"abde1e31fb9da2b963cd138b939e5b91dc4dcfdab55e78f8e7c1b0b5eede0480","abstract_canon_sha256":"413f1a90f4641fc5e6a4401c250ae43a31e8fc3d71a35404aedfc132a57a203d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:11.023535Z","signature_b64":"ghAFA3zYyMKTj+Ba3OIlnbRnNM+MExXyZvBGQ2RNGT/dZAzyAp64DnR7/t5eKs52eRgtBL8wCgeAL4d4WgPlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94ff6eee4acbab0118e690fdeb166b8278060fb6a81f5256dea84b9811549ab7","last_reissued_at":"2026-07-05T02:29:11.022981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:11.022981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FaceGuard: A Self-Supervised Defense Against Adversarial Face Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anil K. Jain, Debayan Deb, Xiaoming Liu","submitted_at":"2020-11-28T21:18:46Z","abstract_excerpt":"Prevailing defense mechanisms against adversarial face images tend to overfit to the adversarial perturbations in the training set and fail to generalize to unseen adversarial attacks. We propose a new self-supervised adversarial defense framework, namely FaceGuard, that can automatically detect, localize, and purify a wide variety of adversarial faces without utilizing pre-computed adversarial training samples. During training, FaceGuard automatically synthesizes challenging and diverse adversarial attacks, enabling a classifier to learn to distinguish them from real faces and a purifier atte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14218","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/2011.14218/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":"2011.14218","created_at":"2026-07-05T02:29:11.023041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.14218v2","created_at":"2026-07-05T02:29:11.023041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14218","created_at":"2026-07-05T02:29:11.023041+00:00"},{"alias_kind":"pith_short_12","alias_value":"ST7W53SKZOVQ","created_at":"2026-07-05T02:29:11.023041+00:00"},{"alias_kind":"pith_short_16","alias_value":"ST7W53SKZOVQCGHG","created_at":"2026-07-05T02:29:11.023041+00:00"},{"alias_kind":"pith_short_8","alias_value":"ST7W53SK","created_at":"2026-07-05T02:29:11.023041+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/ST7W53SKZOVQCGHGSD66WFTLQJ","json":"https://pith.science/pith/ST7W53SKZOVQCGHGSD66WFTLQJ.json","graph_json":"https://pith.science/api/pith-number/ST7W53SKZOVQCGHGSD66WFTLQJ/graph.json","events_json":"https://pith.science/api/pith-number/ST7W53SKZOVQCGHGSD66WFTLQJ/events.json","paper":"https://pith.science/paper/ST7W53SK"},"agent_actions":{"view_html":"https://pith.science/pith/ST7W53SKZOVQCGHGSD66WFTLQJ","download_json":"https://pith.science/pith/ST7W53SKZOVQCGHGSD66WFTLQJ.json","view_paper":"https://pith.science/paper/ST7W53SK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.14218&json=true","fetch_graph":"https://pith.science/api/pith-number/ST7W53SKZOVQCGHGSD66WFTLQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ST7W53SKZOVQCGHGSD66WFTLQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ST7W53SKZOVQCGHGSD66WFTLQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ST7W53SKZOVQCGHGSD66WFTLQJ/action/storage_attestation","attest_author":"https://pith.science/pith/ST7W53SKZOVQCGHGSD66WFTLQJ/action/author_attestation","sign_citation":"https://pith.science/pith/ST7W53SKZOVQCGHGSD66WFTLQJ/action/citation_signature","submit_replication":"https://pith.science/pith/ST7W53SKZOVQCGHGSD66WFTLQJ/action/replication_record"}},"created_at":"2026-07-05T02:29:11.023041+00:00","updated_at":"2026-07-05T02:29:11.023041+00:00"}