{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TSMWVRMHQZNNUBYCNH2P7D6C6E","short_pith_number":"pith:TSMWVRMH","schema_version":"1.0","canonical_sha256":"9c996ac587865ada070269f4ff8fc2f1149100bb11a0d773557d313b64e24e80","source":{"kind":"arxiv","id":"1712.03390","version":2},"attestation_state":"computed","paper":{"title":"NAG: Network for Adversary Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Konda Reddy Mopuri, R. Venkatesh Babu, Utkarsh Ojha, Utsav Garg","submitted_at":"2017-12-09T14:27:49Z","abstract_excerpt":"Adversarial perturbations can pose a serious threat for deploying machine learning systems. Recent works have shown existence of image-agnostic perturbations that can fool classifiers over most natural images. Existing methods present optimization approaches that solve for a fooling objective with an imperceptibility constraint to craft the perturbations. However, for a given classifier, they generate one perturbation at a time, which is a single instance from the manifold of adversarial perturbations. Also, in order to build robust models, it is essential to explore the manifold of adversaria"},"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":"1712.03390","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-09T14:27:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"21421227b910c2e8cd8747c8f866087dfa2e3ceecfd153af74f9689110c24a70","abstract_canon_sha256":"716af2929d0e789f83d6597e70d545771553e10dfe262b4339fdb93f29fdc18b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:56.641555Z","signature_b64":"eUjCA76D9t/NlDrWQ4ySlAW+0dNdXEB7XvWOmemDybGR7EOS5CC1R4ZwFnISueqEpzXXRcCCcPQHNQK44WwXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c996ac587865ada070269f4ff8fc2f1149100bb11a0d773557d313b64e24e80","last_reissued_at":"2026-05-18T00:19:56.640891Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:56.640891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NAG: Network for Adversary Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Konda Reddy Mopuri, R. Venkatesh Babu, Utkarsh Ojha, Utsav Garg","submitted_at":"2017-12-09T14:27:49Z","abstract_excerpt":"Adversarial perturbations can pose a serious threat for deploying machine learning systems. Recent works have shown existence of image-agnostic perturbations that can fool classifiers over most natural images. Existing methods present optimization approaches that solve for a fooling objective with an imperceptibility constraint to craft the perturbations. However, for a given classifier, they generate one perturbation at a time, which is a single instance from the manifold of adversarial perturbations. Also, in order to build robust models, it is essential to explore the manifold of adversaria"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03390","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":""},"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":"1712.03390","created_at":"2026-05-18T00:19:56.640984+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.03390v2","created_at":"2026-05-18T00:19:56.640984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03390","created_at":"2026-05-18T00:19:56.640984+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSMWVRMHQZNN","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSMWVRMHQZNNUBYC","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSMWVRMH","created_at":"2026-05-18T12:31:46.661854+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/TSMWVRMHQZNNUBYCNH2P7D6C6E","json":"https://pith.science/pith/TSMWVRMHQZNNUBYCNH2P7D6C6E.json","graph_json":"https://pith.science/api/pith-number/TSMWVRMHQZNNUBYCNH2P7D6C6E/graph.json","events_json":"https://pith.science/api/pith-number/TSMWVRMHQZNNUBYCNH2P7D6C6E/events.json","paper":"https://pith.science/paper/TSMWVRMH"},"agent_actions":{"view_html":"https://pith.science/pith/TSMWVRMHQZNNUBYCNH2P7D6C6E","download_json":"https://pith.science/pith/TSMWVRMHQZNNUBYCNH2P7D6C6E.json","view_paper":"https://pith.science/paper/TSMWVRMH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.03390&json=true","fetch_graph":"https://pith.science/api/pith-number/TSMWVRMHQZNNUBYCNH2P7D6C6E/graph.json","fetch_events":"https://pith.science/api/pith-number/TSMWVRMHQZNNUBYCNH2P7D6C6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSMWVRMHQZNNUBYCNH2P7D6C6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSMWVRMHQZNNUBYCNH2P7D6C6E/action/storage_attestation","attest_author":"https://pith.science/pith/TSMWVRMHQZNNUBYCNH2P7D6C6E/action/author_attestation","sign_citation":"https://pith.science/pith/TSMWVRMHQZNNUBYCNH2P7D6C6E/action/citation_signature","submit_replication":"https://pith.science/pith/TSMWVRMHQZNNUBYCNH2P7D6C6E/action/replication_record"}},"created_at":"2026-05-18T00:19:56.640984+00:00","updated_at":"2026-05-18T00:19:56.640984+00:00"}