{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3WVZ2VMIYVEGJTCXACHQO3BHEO","short_pith_number":"pith:3WVZ2VMI","schema_version":"1.0","canonical_sha256":"ddab9d5588c54864cc57008f076c27239ab231af53023542f278da0e55cab52f","source":{"kind":"arxiv","id":"2506.05382","version":1},"attestation_state":"computed","paper":{"title":"How stealthy is stealthy? Studying the Efficacy of Black-Box Adversarial Attacks in the Real World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Francesco Panebianco, Mario D'Onghia, Stefano Zanero aand Michele Carminati","submitted_at":"2025-06-03T08:56:37Z","abstract_excerpt":"Deep learning systems, critical in domains like autonomous vehicles, are vulnerable to adversarial examples (crafted inputs designed to mislead classifiers). This study investigates black-box adversarial attacks in computer vision. This is a realistic scenario, where attackers have query-only access to the target model. Three properties are introduced to evaluate attack feasibility: robustness to compression, stealthiness to automatic detection, and stealthiness to human inspection. State-of-the-Art methods tend to prioritize one criterion at the expense of others. We propose ECLIPSE, a novel "},"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":"2506.05382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-06-03T08:56:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a4766d379ecfe1852a3f28a22ba7009384b0dbe68da09f9ce5fb0fbdc0be9e09","abstract_canon_sha256":"cd7109dc1b79edbf539837c5ca03ce59e5e66e36142f1c1a9a3ddb7554a8347c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:01.696934Z","signature_b64":"a3TdQqcwvlyA7oBS14IZlDVWL/JASH5RNxaP9BDzDYpi8lSUbSEP4Q0r5di5Fozv02qW1WKFIcSGp3Lisr2DCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddab9d5588c54864cc57008f076c27239ab231af53023542f278da0e55cab52f","last_reissued_at":"2026-07-05T11:17:01.696478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:01.696478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How stealthy is stealthy? Studying the Efficacy of Black-Box Adversarial Attacks in the Real World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Francesco Panebianco, Mario D'Onghia, Stefano Zanero aand Michele Carminati","submitted_at":"2025-06-03T08:56:37Z","abstract_excerpt":"Deep learning systems, critical in domains like autonomous vehicles, are vulnerable to adversarial examples (crafted inputs designed to mislead classifiers). This study investigates black-box adversarial attacks in computer vision. This is a realistic scenario, where attackers have query-only access to the target model. Three properties are introduced to evaluate attack feasibility: robustness to compression, stealthiness to automatic detection, and stealthiness to human inspection. State-of-the-Art methods tend to prioritize one criterion at the expense of others. We propose ECLIPSE, a novel "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05382","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/2506.05382/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":"2506.05382","created_at":"2026-07-05T11:17:01.696529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05382v1","created_at":"2026-07-05T11:17:01.696529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05382","created_at":"2026-07-05T11:17:01.696529+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WVZ2VMIYVEG","created_at":"2026-07-05T11:17:01.696529+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WVZ2VMIYVEGJTCX","created_at":"2026-07-05T11:17:01.696529+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WVZ2VMI","created_at":"2026-07-05T11:17:01.696529+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/3WVZ2VMIYVEGJTCXACHQO3BHEO","json":"https://pith.science/pith/3WVZ2VMIYVEGJTCXACHQO3BHEO.json","graph_json":"https://pith.science/api/pith-number/3WVZ2VMIYVEGJTCXACHQO3BHEO/graph.json","events_json":"https://pith.science/api/pith-number/3WVZ2VMIYVEGJTCXACHQO3BHEO/events.json","paper":"https://pith.science/paper/3WVZ2VMI"},"agent_actions":{"view_html":"https://pith.science/pith/3WVZ2VMIYVEGJTCXACHQO3BHEO","download_json":"https://pith.science/pith/3WVZ2VMIYVEGJTCXACHQO3BHEO.json","view_paper":"https://pith.science/paper/3WVZ2VMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05382&json=true","fetch_graph":"https://pith.science/api/pith-number/3WVZ2VMIYVEGJTCXACHQO3BHEO/graph.json","fetch_events":"https://pith.science/api/pith-number/3WVZ2VMIYVEGJTCXACHQO3BHEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WVZ2VMIYVEGJTCXACHQO3BHEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WVZ2VMIYVEGJTCXACHQO3BHEO/action/storage_attestation","attest_author":"https://pith.science/pith/3WVZ2VMIYVEGJTCXACHQO3BHEO/action/author_attestation","sign_citation":"https://pith.science/pith/3WVZ2VMIYVEGJTCXACHQO3BHEO/action/citation_signature","submit_replication":"https://pith.science/pith/3WVZ2VMIYVEGJTCXACHQO3BHEO/action/replication_record"}},"created_at":"2026-07-05T11:17:01.696529+00:00","updated_at":"2026-07-05T11:17:01.696529+00:00"}