{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P3IZKHDIFFKOGV45QILSAY3HKR","short_pith_number":"pith:P3IZKHDI","schema_version":"1.0","canonical_sha256":"7ed1951c682954e3579d821720636754449a7bbd25842520d79a29583f53ddde","source":{"kind":"arxiv","id":"2406.05857","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Han, Dongfang Liu, James Liang, Qifan Wang, Xiangyu Zhang, Zhiyuan Cheng","submitted_at":"2024-06-09T17:02:28Z","abstract_excerpt":"Monocular Depth Estimation (MDE) plays a vital role in applications such as autonomous driving. However, various attacks target MDE models, with physical attacks posing significant threats to system security. Traditional adversarial training methods, which require ground-truth labels, are not directly applicable to MDE models that lack ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) overlook the domain knowledge of MDE, resulting in suboptimal performance. In this work, we introduce a novel self-supervised adversarial training approach for MDE m"},"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":"2406.05857","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-09T17:02:28Z","cross_cats_sorted":[],"title_canon_sha256":"eb7479047738873ae075845a0ca87e0482c19d7c315285631c77e08db7750cd0","abstract_canon_sha256":"df1f7ca7d08f9a11e31071d01aa012488410c433fd770b4d79f0c5227d3ac468"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:48.342848Z","signature_b64":"gt4MBy72uu4xaNco9FUzUGBbBUKXxOdp0wzgs6tLwqhNFk4X8HLRS5DrvNu/Di1rfDTVeeNFJe8dBHrBth4hBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ed1951c682954e3579d821720636754449a7bbd25842520d79a29583f53ddde","last_reissued_at":"2026-07-05T08:34:48.342366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:48.342366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Han, Dongfang Liu, James Liang, Qifan Wang, Xiangyu Zhang, Zhiyuan Cheng","submitted_at":"2024-06-09T17:02:28Z","abstract_excerpt":"Monocular Depth Estimation (MDE) plays a vital role in applications such as autonomous driving. However, various attacks target MDE models, with physical attacks posing significant threats to system security. Traditional adversarial training methods, which require ground-truth labels, are not directly applicable to MDE models that lack ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) overlook the domain knowledge of MDE, resulting in suboptimal performance. In this work, we introduce a novel self-supervised adversarial training approach for MDE m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05857","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/2406.05857/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":"2406.05857","created_at":"2026-07-05T08:34:48.342422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05857v1","created_at":"2026-07-05T08:34:48.342422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05857","created_at":"2026-07-05T08:34:48.342422+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3IZKHDIFFKO","created_at":"2026-07-05T08:34:48.342422+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3IZKHDIFFKOGV45","created_at":"2026-07-05T08:34:48.342422+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3IZKHDI","created_at":"2026-07-05T08:34:48.342422+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13587","citing_title":"Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3IZKHDIFFKOGV45QILSAY3HKR","json":"https://pith.science/pith/P3IZKHDIFFKOGV45QILSAY3HKR.json","graph_json":"https://pith.science/api/pith-number/P3IZKHDIFFKOGV45QILSAY3HKR/graph.json","events_json":"https://pith.science/api/pith-number/P3IZKHDIFFKOGV45QILSAY3HKR/events.json","paper":"https://pith.science/paper/P3IZKHDI"},"agent_actions":{"view_html":"https://pith.science/pith/P3IZKHDIFFKOGV45QILSAY3HKR","download_json":"https://pith.science/pith/P3IZKHDIFFKOGV45QILSAY3HKR.json","view_paper":"https://pith.science/paper/P3IZKHDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05857&json=true","fetch_graph":"https://pith.science/api/pith-number/P3IZKHDIFFKOGV45QILSAY3HKR/graph.json","fetch_events":"https://pith.science/api/pith-number/P3IZKHDIFFKOGV45QILSAY3HKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3IZKHDIFFKOGV45QILSAY3HKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3IZKHDIFFKOGV45QILSAY3HKR/action/storage_attestation","attest_author":"https://pith.science/pith/P3IZKHDIFFKOGV45QILSAY3HKR/action/author_attestation","sign_citation":"https://pith.science/pith/P3IZKHDIFFKOGV45QILSAY3HKR/action/citation_signature","submit_replication":"https://pith.science/pith/P3IZKHDIFFKOGV45QILSAY3HKR/action/replication_record"}},"created_at":"2026-07-05T08:34:48.342422+00:00","updated_at":"2026-07-05T08:34:48.342422+00:00"}