{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TRMELPJ7PX7MT2WMBNBK3XPOBE","short_pith_number":"pith:TRMELPJ7","schema_version":"1.0","canonical_sha256":"9c5845bd3f7dfec9eacc0b42adddee0906a27698ec38ee35a70f52652f03bb3d","source":{"kind":"arxiv","id":"2301.13487","version":3},"attestation_state":"computed","paper":{"title":"Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dongfang Liu, Guanhong Tao, James Liang, Xiangyu Zhang, Zhiyuan Cheng","submitted_at":"2023-01-31T09:12:16Z","abstract_excerpt":"Monocular Depth Estimation (MDE) is a critical component in applications such as autonomous driving. There are various attacks against MDE networks. These attacks, especially the physical ones, pose a great threat to the security of such systems. Traditional adversarial training method requires ground-truth labels hence cannot be directly applied to self-supervised MDE that does not have ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) ignore the domain knowledge of MDE and can hardly achieve optimal performance. In this work, we propose 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":"2301.13487","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-31T09:12:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad6851e60b863b5c0b65d1b3ab31674ce47858064e41042856d9789f149de7aa","abstract_canon_sha256":"c33d82cfa638eed632da213c82ce543a9622191373c32bc3f857a362422682e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:15.882390Z","signature_b64":"yIn9lORtPFhN7eBjhA9+UYWgMxjwxbN/keLt0V6VqtSJgszRqL2PupGgsl/zzJdxhVKGb2h9SPAmXUL4USc7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c5845bd3f7dfec9eacc0b42adddee0906a27698ec38ee35a70f52652f03bb3d","last_reissued_at":"2026-07-05T05:57:15.881916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:15.881916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dongfang Liu, Guanhong Tao, James Liang, Xiangyu Zhang, Zhiyuan Cheng","submitted_at":"2023-01-31T09:12:16Z","abstract_excerpt":"Monocular Depth Estimation (MDE) is a critical component in applications such as autonomous driving. There are various attacks against MDE networks. These attacks, especially the physical ones, pose a great threat to the security of such systems. Traditional adversarial training method requires ground-truth labels hence cannot be directly applied to self-supervised MDE that does not have ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) ignore the domain knowledge of MDE and can hardly achieve optimal performance. In this work, we propose a novel "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13487","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/2301.13487/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":"2301.13487","created_at":"2026-07-05T05:57:15.881972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13487v3","created_at":"2026-07-05T05:57:15.881972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13487","created_at":"2026-07-05T05:57:15.881972+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRMELPJ7PX7M","created_at":"2026-07-05T05:57:15.881972+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRMELPJ7PX7MT2WM","created_at":"2026-07-05T05:57:15.881972+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRMELPJ7","created_at":"2026-07-05T05:57:15.881972+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/TRMELPJ7PX7MT2WMBNBK3XPOBE","json":"https://pith.science/pith/TRMELPJ7PX7MT2WMBNBK3XPOBE.json","graph_json":"https://pith.science/api/pith-number/TRMELPJ7PX7MT2WMBNBK3XPOBE/graph.json","events_json":"https://pith.science/api/pith-number/TRMELPJ7PX7MT2WMBNBK3XPOBE/events.json","paper":"https://pith.science/paper/TRMELPJ7"},"agent_actions":{"view_html":"https://pith.science/pith/TRMELPJ7PX7MT2WMBNBK3XPOBE","download_json":"https://pith.science/pith/TRMELPJ7PX7MT2WMBNBK3XPOBE.json","view_paper":"https://pith.science/paper/TRMELPJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13487&json=true","fetch_graph":"https://pith.science/api/pith-number/TRMELPJ7PX7MT2WMBNBK3XPOBE/graph.json","fetch_events":"https://pith.science/api/pith-number/TRMELPJ7PX7MT2WMBNBK3XPOBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRMELPJ7PX7MT2WMBNBK3XPOBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRMELPJ7PX7MT2WMBNBK3XPOBE/action/storage_attestation","attest_author":"https://pith.science/pith/TRMELPJ7PX7MT2WMBNBK3XPOBE/action/author_attestation","sign_citation":"https://pith.science/pith/TRMELPJ7PX7MT2WMBNBK3XPOBE/action/citation_signature","submit_replication":"https://pith.science/pith/TRMELPJ7PX7MT2WMBNBK3XPOBE/action/replication_record"}},"created_at":"2026-07-05T05:57:15.881972+00:00","updated_at":"2026-07-05T05:57:15.881972+00:00"}