{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:E37F7CW3E4CQD3Q35ATI73BC2W","short_pith_number":"pith:E37F7CW3","schema_version":"1.0","canonical_sha256":"26fe5f8adb270501ee1be8268fec22d5a3757e7310fbfc98c34e6cbf2980da63","source":{"kind":"arxiv","id":"1911.08790","version":1},"attestation_state":"computed","paper":{"title":"Analysis of Deep Networks for Monocular Depth Estimation Through Adversarial Attacks with Proposal of a Defense Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junjie Hu, Takayuki Okatani","submitted_at":"2019-11-20T09:41:53Z","abstract_excerpt":"In this paper, we consider adversarial attacks against a system of monocular depth estimation (MDE) based on convolutional neural networks (CNNs). The motivation is two-fold. One is to study the security of MDE systems, which has not been actively considered in the community. The other is to improve our understanding of the computational mechanism of CNNs performing MDE. Toward this end, we apply the method recently proposed for visualization of MDE to defending attacks. It trains another CNN to predict a saliency map from an input image, such that the CNN for MDE continues to accurately estim"},"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":"1911.08790","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-20T09:41:53Z","cross_cats_sorted":[],"title_canon_sha256":"45f583453a29de21d3838b945b3a4b7e418184dfd9fe34d8bded8e3e4c84b060","abstract_canon_sha256":"ca796cb594e5b0ae0c6a2177596f1796386f1f93ce91ebbffc61c8c1a95ed0e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:45.624211Z","signature_b64":"yIFJYxn9qdcRRQwHxnK//v6OcTHhIzfyceVagvLxWHIwHdGt3fDM2eiX7LISLtLJlkZ8DpGCm3f9KEj32wrgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26fe5f8adb270501ee1be8268fec22d5a3757e7310fbfc98c34e6cbf2980da63","last_reissued_at":"2026-07-05T00:20:45.623633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:45.623633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysis of Deep Networks for Monocular Depth Estimation Through Adversarial Attacks with Proposal of a Defense Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junjie Hu, Takayuki Okatani","submitted_at":"2019-11-20T09:41:53Z","abstract_excerpt":"In this paper, we consider adversarial attacks against a system of monocular depth estimation (MDE) based on convolutional neural networks (CNNs). The motivation is two-fold. One is to study the security of MDE systems, which has not been actively considered in the community. The other is to improve our understanding of the computational mechanism of CNNs performing MDE. Toward this end, we apply the method recently proposed for visualization of MDE to defending attacks. It trains another CNN to predict a saliency map from an input image, such that the CNN for MDE continues to accurately estim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.08790","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/1911.08790/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":"1911.08790","created_at":"2026-07-05T00:20:45.623719+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.08790v1","created_at":"2026-07-05T00:20:45.623719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.08790","created_at":"2026-07-05T00:20:45.623719+00:00"},{"alias_kind":"pith_short_12","alias_value":"E37F7CW3E4CQ","created_at":"2026-07-05T00:20:45.623719+00:00"},{"alias_kind":"pith_short_16","alias_value":"E37F7CW3E4CQD3Q3","created_at":"2026-07-05T00:20:45.623719+00:00"},{"alias_kind":"pith_short_8","alias_value":"E37F7CW3","created_at":"2026-07-05T00:20:45.623719+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16154","citing_title":"BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E37F7CW3E4CQD3Q35ATI73BC2W","json":"https://pith.science/pith/E37F7CW3E4CQD3Q35ATI73BC2W.json","graph_json":"https://pith.science/api/pith-number/E37F7CW3E4CQD3Q35ATI73BC2W/graph.json","events_json":"https://pith.science/api/pith-number/E37F7CW3E4CQD3Q35ATI73BC2W/events.json","paper":"https://pith.science/paper/E37F7CW3"},"agent_actions":{"view_html":"https://pith.science/pith/E37F7CW3E4CQD3Q35ATI73BC2W","download_json":"https://pith.science/pith/E37F7CW3E4CQD3Q35ATI73BC2W.json","view_paper":"https://pith.science/paper/E37F7CW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.08790&json=true","fetch_graph":"https://pith.science/api/pith-number/E37F7CW3E4CQD3Q35ATI73BC2W/graph.json","fetch_events":"https://pith.science/api/pith-number/E37F7CW3E4CQD3Q35ATI73BC2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E37F7CW3E4CQD3Q35ATI73BC2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E37F7CW3E4CQD3Q35ATI73BC2W/action/storage_attestation","attest_author":"https://pith.science/pith/E37F7CW3E4CQD3Q35ATI73BC2W/action/author_attestation","sign_citation":"https://pith.science/pith/E37F7CW3E4CQD3Q35ATI73BC2W/action/citation_signature","submit_replication":"https://pith.science/pith/E37F7CW3E4CQD3Q35ATI73BC2W/action/replication_record"}},"created_at":"2026-07-05T00:20:45.623719+00:00","updated_at":"2026-07-05T00:20:45.623719+00:00"}