{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:W4DOIU5G4NUAEPBKGGMNQVYRBJ","short_pith_number":"pith:W4DOIU5G","schema_version":"1.0","canonical_sha256":"b706e453a6e368023c2a3198d857110a5bf299ab918d126c7c54f556ea6258d2","source":{"kind":"arxiv","id":"2108.06179","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attacks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessandro Biondi, Federico Nesti, Giorgio Buttazzo, Giulio Rossolini, Saasha Nair","submitted_at":"2021-08-13T11:49:09Z","abstract_excerpt":"Deep learning and convolutional neural networks allow achieving impressive performance in computer vision tasks, such as object detection and semantic segmentation (SS). However, recent studies have shown evident weaknesses of such models against adversarial perturbations. In a real-world scenario instead, like autonomous driving, more attention should be devoted to real-world adversarial examples (RWAEs), which are physical objects (e.g., billboards and printable patches) optimized to be adversarial to the entire perception pipeline. This paper presents an in-depth evaluation of the robustnes"},"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":"2108.06179","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-13T11:49:09Z","cross_cats_sorted":[],"title_canon_sha256":"dd9d983d71f1da881bb57c819f18bf99da902510de1f6648d8afce6b35f714e0","abstract_canon_sha256":"d7c0384329bc888b6974732790591300729e99b5ea2f3dffb3f34bbdecbb7bda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:38.329952Z","signature_b64":"b9Ojtoos0lHu+v+zICNbwk48RyEfBegy7JCacmnx4YaMzfGCx2JU1yLwVECBSq6LCZAnlOuhw1jWXVfnBzV4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b706e453a6e368023c2a3198d857110a5bf299ab918d126c7c54f556ea6258d2","last_reissued_at":"2026-07-05T03:05:38.329441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:38.329441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attacks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessandro Biondi, Federico Nesti, Giorgio Buttazzo, Giulio Rossolini, Saasha Nair","submitted_at":"2021-08-13T11:49:09Z","abstract_excerpt":"Deep learning and convolutional neural networks allow achieving impressive performance in computer vision tasks, such as object detection and semantic segmentation (SS). However, recent studies have shown evident weaknesses of such models against adversarial perturbations. In a real-world scenario instead, like autonomous driving, more attention should be devoted to real-world adversarial examples (RWAEs), which are physical objects (e.g., billboards and printable patches) optimized to be adversarial to the entire perception pipeline. This paper presents an in-depth evaluation of the robustnes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.06179","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/2108.06179/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":"2108.06179","created_at":"2026-07-05T03:05:38.329535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.06179v1","created_at":"2026-07-05T03:05:38.329535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.06179","created_at":"2026-07-05T03:05:38.329535+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4DOIU5G4NUA","created_at":"2026-07-05T03:05:38.329535+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4DOIU5G4NUAEPBK","created_at":"2026-07-05T03:05:38.329535+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4DOIU5G","created_at":"2026-07-05T03:05:38.329535+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/W4DOIU5G4NUAEPBKGGMNQVYRBJ","json":"https://pith.science/pith/W4DOIU5G4NUAEPBKGGMNQVYRBJ.json","graph_json":"https://pith.science/api/pith-number/W4DOIU5G4NUAEPBKGGMNQVYRBJ/graph.json","events_json":"https://pith.science/api/pith-number/W4DOIU5G4NUAEPBKGGMNQVYRBJ/events.json","paper":"https://pith.science/paper/W4DOIU5G"},"agent_actions":{"view_html":"https://pith.science/pith/W4DOIU5G4NUAEPBKGGMNQVYRBJ","download_json":"https://pith.science/pith/W4DOIU5G4NUAEPBKGGMNQVYRBJ.json","view_paper":"https://pith.science/paper/W4DOIU5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.06179&json=true","fetch_graph":"https://pith.science/api/pith-number/W4DOIU5G4NUAEPBKGGMNQVYRBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/W4DOIU5G4NUAEPBKGGMNQVYRBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4DOIU5G4NUAEPBKGGMNQVYRBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4DOIU5G4NUAEPBKGGMNQVYRBJ/action/storage_attestation","attest_author":"https://pith.science/pith/W4DOIU5G4NUAEPBKGGMNQVYRBJ/action/author_attestation","sign_citation":"https://pith.science/pith/W4DOIU5G4NUAEPBKGGMNQVYRBJ/action/citation_signature","submit_replication":"https://pith.science/pith/W4DOIU5G4NUAEPBKGGMNQVYRBJ/action/replication_record"}},"created_at":"2026-07-05T03:05:38.329535+00:00","updated_at":"2026-07-05T03:05:38.329535+00:00"}