{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RMBFCDJYSGPMATWLYBYMHEEDKX","short_pith_number":"pith:RMBFCDJY","schema_version":"1.0","canonical_sha256":"8b02510d38919ec04ecbc070c3908355eff0c5163ec84ca0d00fa1a5e9173065","source":{"kind":"arxiv","id":"1808.01153","version":1},"attestation_state":"computed","paper":{"title":"Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Konda Reddy Mopuri, Phani Krishna Uppala, R. Venkatesh Babu","submitted_at":"2018-08-03T11:02:26Z","abstract_excerpt":"Deep learning models are susceptible to input specific noise, called adversarial perturbations. Moreover, there exist input-agnostic noise, called Universal Adversarial Perturbations (UAP) that can affect inference of the models over most input samples. Given a model, there exist broadly two approaches to craft UAPs: (i) data-driven: that require data, and (ii) data-free: that do not require data samples. Data-driven approaches require actual samples from the underlying data distribution and craft UAPs with high success (fooling) rate. However, data-free approaches craft UAPs without utilizing"},"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":"1808.01153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-03T11:02:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4858fef3deb960432f5323ea636243061b9c40424f707742880b9b2345c1cb37","abstract_canon_sha256":"9c98e283c13de592d46f965fa07d66c282906ed4676c803d1563441f2e19487c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:58.842221Z","signature_b64":"cIY06VRBa4X27zRE/1FOhUQoTH0ha7yn7vUY9TYXLjgXq6bdoiU9Lwcdzb55tc5JvjvwLKC6h9/SLLj72kjvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b02510d38919ec04ecbc070c3908355eff0c5163ec84ca0d00fa1a5e9173065","last_reissued_at":"2026-05-18T00:08:58.841629Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:58.841629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Konda Reddy Mopuri, Phani Krishna Uppala, R. Venkatesh Babu","submitted_at":"2018-08-03T11:02:26Z","abstract_excerpt":"Deep learning models are susceptible to input specific noise, called adversarial perturbations. Moreover, there exist input-agnostic noise, called Universal Adversarial Perturbations (UAP) that can affect inference of the models over most input samples. Given a model, there exist broadly two approaches to craft UAPs: (i) data-driven: that require data, and (ii) data-free: that do not require data samples. Data-driven approaches require actual samples from the underlying data distribution and craft UAPs with high success (fooling) rate. However, data-free approaches craft UAPs without utilizing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01153","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":""},"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":"1808.01153","created_at":"2026-05-18T00:08:58.841738+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.01153v1","created_at":"2026-05-18T00:08:58.841738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01153","created_at":"2026-05-18T00:08:58.841738+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMBFCDJYSGPM","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMBFCDJYSGPMATWL","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMBFCDJY","created_at":"2026-05-18T12:32:50.500415+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/RMBFCDJYSGPMATWLYBYMHEEDKX","json":"https://pith.science/pith/RMBFCDJYSGPMATWLYBYMHEEDKX.json","graph_json":"https://pith.science/api/pith-number/RMBFCDJYSGPMATWLYBYMHEEDKX/graph.json","events_json":"https://pith.science/api/pith-number/RMBFCDJYSGPMATWLYBYMHEEDKX/events.json","paper":"https://pith.science/paper/RMBFCDJY"},"agent_actions":{"view_html":"https://pith.science/pith/RMBFCDJYSGPMATWLYBYMHEEDKX","download_json":"https://pith.science/pith/RMBFCDJYSGPMATWLYBYMHEEDKX.json","view_paper":"https://pith.science/paper/RMBFCDJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.01153&json=true","fetch_graph":"https://pith.science/api/pith-number/RMBFCDJYSGPMATWLYBYMHEEDKX/graph.json","fetch_events":"https://pith.science/api/pith-number/RMBFCDJYSGPMATWLYBYMHEEDKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMBFCDJYSGPMATWLYBYMHEEDKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMBFCDJYSGPMATWLYBYMHEEDKX/action/storage_attestation","attest_author":"https://pith.science/pith/RMBFCDJYSGPMATWLYBYMHEEDKX/action/author_attestation","sign_citation":"https://pith.science/pith/RMBFCDJYSGPMATWLYBYMHEEDKX/action/citation_signature","submit_replication":"https://pith.science/pith/RMBFCDJYSGPMATWLYBYMHEEDKX/action/replication_record"}},"created_at":"2026-05-18T00:08:58.841738+00:00","updated_at":"2026-05-18T00:08:58.841738+00:00"}