{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SF3YBOEMQ7XVATAVIQQOOOSNPQ","short_pith_number":"pith:SF3YBOEM","schema_version":"1.0","canonical_sha256":"917780b88c87ef504c154420e73a4d7c1c3ae36a195a6520cc08de80675413f8","source":{"kind":"arxiv","id":"2505.06477","version":1},"attestation_state":"computed","paper":{"title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Gargi Mitra, Karthik Pattabiraman, Mohammed Elnawawy, Shahrear Iqbal","submitted_at":"2025-05-10T00:33:15Z","abstract_excerpt":"Safety-critical applications such as healthcare and autonomous vehicles use deep neural networks (DNN) to make predictions and infer decisions. DNNs are susceptible to evasion attacks, where an adversary crafts a malicious data instance to trick the DNN into making wrong decisions at inference time. Existing defenses that protect DNNs against evasion attacks are either static or dynamic. Static defenses are computationally efficient but do not adapt to the evolving threat landscape, while dynamic defenses are adaptable but suffer from an increased computational overhead. To combine the best of"},"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":"2505.06477","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-05-10T00:33:15Z","cross_cats_sorted":[],"title_canon_sha256":"cd13eb57c145568eaf0df20acd057911bad3736093a002c448877815e00831fe","abstract_canon_sha256":"5af9c60177919e247de8bd5234ba738148e5e4e9f62bd569de005d61b59e79eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:10.202744Z","signature_b64":"lJKWJO17ucelChKIm/qz8NcC6HlNGMbn5jObP6X9GoAGYigmB6utlBNYYPmnNCGQj2JObtkulX/DlG1c8q15Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"917780b88c87ef504c154420e73a4d7c1c3ae36a195a6520cc08de80675413f8","last_reissued_at":"2026-07-05T11:01:10.202170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:10.202170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Gargi Mitra, Karthik Pattabiraman, Mohammed Elnawawy, Shahrear Iqbal","submitted_at":"2025-05-10T00:33:15Z","abstract_excerpt":"Safety-critical applications such as healthcare and autonomous vehicles use deep neural networks (DNN) to make predictions and infer decisions. DNNs are susceptible to evasion attacks, where an adversary crafts a malicious data instance to trick the DNN into making wrong decisions at inference time. Existing defenses that protect DNNs against evasion attacks are either static or dynamic. Static defenses are computationally efficient but do not adapt to the evolving threat landscape, while dynamic defenses are adaptable but suffer from an increased computational overhead. To combine the best of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06477","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.06477/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":"2505.06477","created_at":"2026-07-05T11:01:10.202233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06477v1","created_at":"2026-07-05T11:01:10.202233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06477","created_at":"2026-07-05T11:01:10.202233+00:00"},{"alias_kind":"pith_short_12","alias_value":"SF3YBOEMQ7XV","created_at":"2026-07-05T11:01:10.202233+00:00"},{"alias_kind":"pith_short_16","alias_value":"SF3YBOEMQ7XVATAV","created_at":"2026-07-05T11:01:10.202233+00:00"},{"alias_kind":"pith_short_8","alias_value":"SF3YBOEM","created_at":"2026-07-05T11:01:10.202233+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/SF3YBOEMQ7XVATAVIQQOOOSNPQ","json":"https://pith.science/pith/SF3YBOEMQ7XVATAVIQQOOOSNPQ.json","graph_json":"https://pith.science/api/pith-number/SF3YBOEMQ7XVATAVIQQOOOSNPQ/graph.json","events_json":"https://pith.science/api/pith-number/SF3YBOEMQ7XVATAVIQQOOOSNPQ/events.json","paper":"https://pith.science/paper/SF3YBOEM"},"agent_actions":{"view_html":"https://pith.science/pith/SF3YBOEMQ7XVATAVIQQOOOSNPQ","download_json":"https://pith.science/pith/SF3YBOEMQ7XVATAVIQQOOOSNPQ.json","view_paper":"https://pith.science/paper/SF3YBOEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06477&json=true","fetch_graph":"https://pith.science/api/pith-number/SF3YBOEMQ7XVATAVIQQOOOSNPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SF3YBOEMQ7XVATAVIQQOOOSNPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SF3YBOEMQ7XVATAVIQQOOOSNPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SF3YBOEMQ7XVATAVIQQOOOSNPQ/action/storage_attestation","attest_author":"https://pith.science/pith/SF3YBOEMQ7XVATAVIQQOOOSNPQ/action/author_attestation","sign_citation":"https://pith.science/pith/SF3YBOEMQ7XVATAVIQQOOOSNPQ/action/citation_signature","submit_replication":"https://pith.science/pith/SF3YBOEMQ7XVATAVIQQOOOSNPQ/action/replication_record"}},"created_at":"2026-07-05T11:01:10.202233+00:00","updated_at":"2026-07-05T11:01:10.202233+00:00"}