{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UR47TZ4JN2QQVFKGIEXZ3VJG7L","short_pith_number":"pith:UR47TZ4J","schema_version":"1.0","canonical_sha256":"a479f9e7896ea10a9546412f9dd526fae4cb0ebe2e8fd14f08d3dfdced5412e0","source":{"kind":"arxiv","id":"1805.07894","version":4},"attestation_state":"computed","paper":{"title":"Constructing Unrestricted Adversarial Examples with Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nate Kushman, Rui Shu, Stefano Ermon, Yang Song","submitted_at":"2018-05-21T05:19:08Z","abstract_excerpt":"Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose unrestricted adversarial examples, a new threat model where the attackers are not restricted to small norm-bounded perturbations. Different from perturbation-based attacks, we propose to synthesize unrestricted adversarial examples entirely from scratch using conditional generative models. Specifically, we first train an Auxiliary Classifier Generative Adversarial Network (AC-GA"},"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":"1805.07894","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T05:19:08Z","cross_cats_sorted":["cs.AI","cs.CR","cs.CV","stat.ML"],"title_canon_sha256":"5b1aecf665c58ef3f3ce47d12e694c4750f0e66e95554b71c84d44c521056c0b","abstract_canon_sha256":"b047eed74a6aa8f8a5985238ca5241e00b14e5d61826e64e8cb0ca6c98aed032"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:22.704084Z","signature_b64":"KVSLY4aQdWvPmTrIxxXQ8JqEbC5yihvPqYASBdfrOdWwwRxQKU2tTdin0pAYYFDkpb8pwlitMsydmH70fF1WCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a479f9e7896ea10a9546412f9dd526fae4cb0ebe2e8fd14f08d3dfdced5412e0","last_reissued_at":"2026-05-17T23:59:22.703727Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:22.703727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constructing Unrestricted Adversarial Examples with Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nate Kushman, Rui Shu, Stefano Ermon, Yang Song","submitted_at":"2018-05-21T05:19:08Z","abstract_excerpt":"Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose unrestricted adversarial examples, a new threat model where the attackers are not restricted to small norm-bounded perturbations. Different from perturbation-based attacks, we propose to synthesize unrestricted adversarial examples entirely from scratch using conditional generative models. Specifically, we first train an Auxiliary Classifier Generative Adversarial Network (AC-GA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07894","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1805.07894","created_at":"2026-05-17T23:59:22.703789+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.07894v4","created_at":"2026-05-17T23:59:22.703789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07894","created_at":"2026-05-17T23:59:22.703789+00:00"},{"alias_kind":"pith_short_12","alias_value":"UR47TZ4JN2QQ","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UR47TZ4JN2QQVFKG","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UR47TZ4J","created_at":"2026-05-18T12:32:56.356000+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/UR47TZ4JN2QQVFKGIEXZ3VJG7L","json":"https://pith.science/pith/UR47TZ4JN2QQVFKGIEXZ3VJG7L.json","graph_json":"https://pith.science/api/pith-number/UR47TZ4JN2QQVFKGIEXZ3VJG7L/graph.json","events_json":"https://pith.science/api/pith-number/UR47TZ4JN2QQVFKGIEXZ3VJG7L/events.json","paper":"https://pith.science/paper/UR47TZ4J"},"agent_actions":{"view_html":"https://pith.science/pith/UR47TZ4JN2QQVFKGIEXZ3VJG7L","download_json":"https://pith.science/pith/UR47TZ4JN2QQVFKGIEXZ3VJG7L.json","view_paper":"https://pith.science/paper/UR47TZ4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.07894&json=true","fetch_graph":"https://pith.science/api/pith-number/UR47TZ4JN2QQVFKGIEXZ3VJG7L/graph.json","fetch_events":"https://pith.science/api/pith-number/UR47TZ4JN2QQVFKGIEXZ3VJG7L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UR47TZ4JN2QQVFKGIEXZ3VJG7L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UR47TZ4JN2QQVFKGIEXZ3VJG7L/action/storage_attestation","attest_author":"https://pith.science/pith/UR47TZ4JN2QQVFKGIEXZ3VJG7L/action/author_attestation","sign_citation":"https://pith.science/pith/UR47TZ4JN2QQVFKGIEXZ3VJG7L/action/citation_signature","submit_replication":"https://pith.science/pith/UR47TZ4JN2QQVFKGIEXZ3VJG7L/action/replication_record"}},"created_at":"2026-05-17T23:59:22.703789+00:00","updated_at":"2026-05-17T23:59:22.703789+00:00"}