{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KVZH7RLXZILBCWAC3U6A2YRCMK","short_pith_number":"pith:KVZH7RLX","schema_version":"1.0","canonical_sha256":"55727fc577ca16115802dd3c0d62226293aa4d153b51e7f519d2b27f52282489","source":{"kind":"arxiv","id":"2207.04718","version":1},"attestation_state":"computed","paper":{"title":"Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongfang Liu, Guanhong Tao, Hongjun Choi, James Liang, Xiangyu Zhang, Zhiwen Cao, Zhiyuan Cheng","submitted_at":"2022-07-11T08:59:09Z","abstract_excerpt":"Deep learning has substantially boosted the performance of Monocular Depth Estimation (MDE), a critical component in fully vision-based autonomous driving (AD) systems (e.g., Tesla and Toyota). In this work, we develop an attack against learning-based MDE. In particular, we use an optimization-based method to systematically generate stealthy physical-object-oriented adversarial patches to attack depth estimation. We balance the stealth and effectiveness of our attack with object-oriented adversarial design, sensitive region localization, and natural style camouflage. Using real-world driving s"},"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":"2207.04718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-11T08:59:09Z","cross_cats_sorted":[],"title_canon_sha256":"8ff14a5e940361d9abd6d446fd744f75de7d7462e054d1b284ed1c22777d1673","abstract_canon_sha256":"ef2674f5c42c4966a7984949ed27ae2c3def030cd26d68d1167c04e8acd71740"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:02.726261Z","signature_b64":"o3IzW+VQmDLef7CpmjPKudNOaN6L/9a4IsGzoBdI7CNl8nmLoAEZFwEAqU7Fxh9/Kh3qNnNFuERBYWTDOKpJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55727fc577ca16115802dd3c0d62226293aa4d153b51e7f519d2b27f52282489","last_reissued_at":"2026-07-05T04:39:02.725825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:02.725825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongfang Liu, Guanhong Tao, Hongjun Choi, James Liang, Xiangyu Zhang, Zhiwen Cao, Zhiyuan Cheng","submitted_at":"2022-07-11T08:59:09Z","abstract_excerpt":"Deep learning has substantially boosted the performance of Monocular Depth Estimation (MDE), a critical component in fully vision-based autonomous driving (AD) systems (e.g., Tesla and Toyota). In this work, we develop an attack against learning-based MDE. In particular, we use an optimization-based method to systematically generate stealthy physical-object-oriented adversarial patches to attack depth estimation. We balance the stealth and effectiveness of our attack with object-oriented adversarial design, sensitive region localization, and natural style camouflage. Using real-world driving s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04718","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/2207.04718/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":"2207.04718","created_at":"2026-07-05T04:39:02.725895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.04718v1","created_at":"2026-07-05T04:39:02.725895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04718","created_at":"2026-07-05T04:39:02.725895+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVZH7RLXZILB","created_at":"2026-07-05T04:39:02.725895+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVZH7RLXZILBCWAC","created_at":"2026-07-05T04:39:02.725895+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVZH7RLX","created_at":"2026-07-05T04:39:02.725895+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":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVZH7RLXZILBCWAC3U6A2YRCMK","json":"https://pith.science/pith/KVZH7RLXZILBCWAC3U6A2YRCMK.json","graph_json":"https://pith.science/api/pith-number/KVZH7RLXZILBCWAC3U6A2YRCMK/graph.json","events_json":"https://pith.science/api/pith-number/KVZH7RLXZILBCWAC3U6A2YRCMK/events.json","paper":"https://pith.science/paper/KVZH7RLX"},"agent_actions":{"view_html":"https://pith.science/pith/KVZH7RLXZILBCWAC3U6A2YRCMK","download_json":"https://pith.science/pith/KVZH7RLXZILBCWAC3U6A2YRCMK.json","view_paper":"https://pith.science/paper/KVZH7RLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.04718&json=true","fetch_graph":"https://pith.science/api/pith-number/KVZH7RLXZILBCWAC3U6A2YRCMK/graph.json","fetch_events":"https://pith.science/api/pith-number/KVZH7RLXZILBCWAC3U6A2YRCMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVZH7RLXZILBCWAC3U6A2YRCMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVZH7RLXZILBCWAC3U6A2YRCMK/action/storage_attestation","attest_author":"https://pith.science/pith/KVZH7RLXZILBCWAC3U6A2YRCMK/action/author_attestation","sign_citation":"https://pith.science/pith/KVZH7RLXZILBCWAC3U6A2YRCMK/action/citation_signature","submit_replication":"https://pith.science/pith/KVZH7RLXZILBCWAC3U6A2YRCMK/action/replication_record"}},"created_at":"2026-07-05T04:39:02.725895+00:00","updated_at":"2026-07-05T04:39:02.725895+00:00"}