{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SHRZV6Q3UNLKXQZ5S5IZZMLHO7","short_pith_number":"pith:SHRZV6Q3","schema_version":"1.0","canonical_sha256":"91e39afa1ba356abc33d97519cb16777d43f07d7b98d3ef5913f9947433d5fee","source":{"kind":"arxiv","id":"1907.04449","version":3},"attestation_state":"computed","paper":{"title":"PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ang Li, Cong Liu, Junfeng Guo, Zelun Kong","submitted_at":"2019-07-09T22:46:10Z","abstract_excerpt":"Although Deep neural networks (DNNs) are being pervasively used in vision-based autonomous driving systems, they are found vulnerable to adversarial attacks where small-magnitude perturbations into the inputs during test time cause dramatic changes to the outputs. While most of the recent attack methods target at digital-world adversarial scenarios, it is unclear how they perform in the physical world, and more importantly, the generated perturbations under such methods would cover a whole driving scene including those fixed background imagery such as the sky, making them inapplicable to physi"},"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":"1907.04449","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-09T22:46:10Z","cross_cats_sorted":[],"title_canon_sha256":"205673f7e64521992a3e2bd6868db6d8b414379e41963b63be6f9db013f1f0ab","abstract_canon_sha256":"ae24393e44f352bb18ef6d5f8e9a78b6a2e4550c62588b5903406a34d5502d82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:40.134609Z","signature_b64":"SzwoxDtvaO8sWemqS3pK/Mgv/bCpCMirJtQ1MJWK+325WB2OJNlx/JFedWW9OlkS3YQGiJ/4tIE5TFwu3WqVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91e39afa1ba356abc33d97519cb16777d43f07d7b98d3ef5913f9947433d5fee","last_reissued_at":"2026-07-05T02:39:40.134100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:40.134100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ang Li, Cong Liu, Junfeng Guo, Zelun Kong","submitted_at":"2019-07-09T22:46:10Z","abstract_excerpt":"Although Deep neural networks (DNNs) are being pervasively used in vision-based autonomous driving systems, they are found vulnerable to adversarial attacks where small-magnitude perturbations into the inputs during test time cause dramatic changes to the outputs. While most of the recent attack methods target at digital-world adversarial scenarios, it is unclear how they perform in the physical world, and more importantly, the generated perturbations under such methods would cover a whole driving scene including those fixed background imagery such as the sky, making them inapplicable to physi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04449","kind":"arxiv","version":3},"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/1907.04449/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":"1907.04449","created_at":"2026-07-05T02:39:40.134158+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.04449v3","created_at":"2026-07-05T02:39:40.134158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04449","created_at":"2026-07-05T02:39:40.134158+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHRZV6Q3UNLK","created_at":"2026-07-05T02:39:40.134158+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHRZV6Q3UNLKXQZ5","created_at":"2026-07-05T02:39:40.134158+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHRZV6Q3","created_at":"2026-07-05T02:39:40.134158+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10371","citing_title":"Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SHRZV6Q3UNLKXQZ5S5IZZMLHO7","json":"https://pith.science/pith/SHRZV6Q3UNLKXQZ5S5IZZMLHO7.json","graph_json":"https://pith.science/api/pith-number/SHRZV6Q3UNLKXQZ5S5IZZMLHO7/graph.json","events_json":"https://pith.science/api/pith-number/SHRZV6Q3UNLKXQZ5S5IZZMLHO7/events.json","paper":"https://pith.science/paper/SHRZV6Q3"},"agent_actions":{"view_html":"https://pith.science/pith/SHRZV6Q3UNLKXQZ5S5IZZMLHO7","download_json":"https://pith.science/pith/SHRZV6Q3UNLKXQZ5S5IZZMLHO7.json","view_paper":"https://pith.science/paper/SHRZV6Q3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.04449&json=true","fetch_graph":"https://pith.science/api/pith-number/SHRZV6Q3UNLKXQZ5S5IZZMLHO7/graph.json","fetch_events":"https://pith.science/api/pith-number/SHRZV6Q3UNLKXQZ5S5IZZMLHO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHRZV6Q3UNLKXQZ5S5IZZMLHO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHRZV6Q3UNLKXQZ5S5IZZMLHO7/action/storage_attestation","attest_author":"https://pith.science/pith/SHRZV6Q3UNLKXQZ5S5IZZMLHO7/action/author_attestation","sign_citation":"https://pith.science/pith/SHRZV6Q3UNLKXQZ5S5IZZMLHO7/action/citation_signature","submit_replication":"https://pith.science/pith/SHRZV6Q3UNLKXQZ5S5IZZMLHO7/action/replication_record"}},"created_at":"2026-07-05T02:39:40.134158+00:00","updated_at":"2026-07-05T02:39:40.134158+00:00"}