{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:34OI7K5K5QMBSX43QFFREVEOJV","short_pith_number":"pith:34OI7K5K","schema_version":"1.0","canonical_sha256":"df1c8fabaaec18195f9b814b12548e4d45efacb93f4d355dd0807bbbd986d65c","source":{"kind":"arxiv","id":"1707.05572","version":1},"attestation_state":"computed","paper":{"title":"Fast Feature Fool: A data independent approach to universal adversarial perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Konda Reddy Mopuri, R. Venkatesh Babu, Utsav Garg","submitted_at":"2017-07-18T11:48:14Z","abstract_excerpt":"State-of-the-art object recognition Convolutional Neural Networks (CNNs) are shown to be fooled by image agnostic perturbations, called universal adversarial perturbations. It is also observed that these perturbations generalize across multiple networks trained on the same target data. However, these algorithms require training data on which the CNNs were trained and compute adversarial perturbations via complex optimization. The fooling performance of these approaches is directly proportional to the amount of available training data. This makes them unsuitable for practical attacks since its "},"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":"1707.05572","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-18T11:48:14Z","cross_cats_sorted":[],"title_canon_sha256":"045268eecb495f25fc736c34a989f864f149516dd35151cf8c2a1c1fb9e940ea","abstract_canon_sha256":"877c58eb32788ad20b295a16d4d41a9d6d6e744f1f6dafdeebbf1828e7c57f66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:01.977515Z","signature_b64":"4rfPXy0NVwU4MFbdJwXEIF8E6IMhEFE0HSq3lTQcW4rwiVWHq4y7eWnOFeuOwbPlQ1FBw9DaSaFee3KuRKzhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df1c8fabaaec18195f9b814b12548e4d45efacb93f4d355dd0807bbbd986d65c","last_reissued_at":"2026-05-18T00:40:01.977032Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:01.977032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Feature Fool: A data independent approach to universal adversarial perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Konda Reddy Mopuri, R. Venkatesh Babu, Utsav Garg","submitted_at":"2017-07-18T11:48:14Z","abstract_excerpt":"State-of-the-art object recognition Convolutional Neural Networks (CNNs) are shown to be fooled by image agnostic perturbations, called universal adversarial perturbations. It is also observed that these perturbations generalize across multiple networks trained on the same target data. However, these algorithms require training data on which the CNNs were trained and compute adversarial perturbations via complex optimization. The fooling performance of these approaches is directly proportional to the amount of available training data. This makes them unsuitable for practical attacks since its "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.05572","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":"1707.05572","created_at":"2026-05-18T00:40:01.977122+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.05572v1","created_at":"2026-05-18T00:40:01.977122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.05572","created_at":"2026-05-18T00:40:01.977122+00:00"},{"alias_kind":"pith_short_12","alias_value":"34OI7K5K5QMB","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"34OI7K5K5QMBSX43","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"34OI7K5K","created_at":"2026-05-18T12:30:58.224056+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/34OI7K5K5QMBSX43QFFREVEOJV","json":"https://pith.science/pith/34OI7K5K5QMBSX43QFFREVEOJV.json","graph_json":"https://pith.science/api/pith-number/34OI7K5K5QMBSX43QFFREVEOJV/graph.json","events_json":"https://pith.science/api/pith-number/34OI7K5K5QMBSX43QFFREVEOJV/events.json","paper":"https://pith.science/paper/34OI7K5K"},"agent_actions":{"view_html":"https://pith.science/pith/34OI7K5K5QMBSX43QFFREVEOJV","download_json":"https://pith.science/pith/34OI7K5K5QMBSX43QFFREVEOJV.json","view_paper":"https://pith.science/paper/34OI7K5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.05572&json=true","fetch_graph":"https://pith.science/api/pith-number/34OI7K5K5QMBSX43QFFREVEOJV/graph.json","fetch_events":"https://pith.science/api/pith-number/34OI7K5K5QMBSX43QFFREVEOJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34OI7K5K5QMBSX43QFFREVEOJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34OI7K5K5QMBSX43QFFREVEOJV/action/storage_attestation","attest_author":"https://pith.science/pith/34OI7K5K5QMBSX43QFFREVEOJV/action/author_attestation","sign_citation":"https://pith.science/pith/34OI7K5K5QMBSX43QFFREVEOJV/action/citation_signature","submit_replication":"https://pith.science/pith/34OI7K5K5QMBSX43QFFREVEOJV/action/replication_record"}},"created_at":"2026-05-18T00:40:01.977122+00:00","updated_at":"2026-05-18T00:40:01.977122+00:00"}