{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y3LPDYW424GYUJPXMTSW42RHGU","short_pith_number":"pith:Y3LPDYW4","schema_version":"1.0","canonical_sha256":"c6d6f1e2dcd70d8a25f764e56e6a2735029a1019f06afd377430e9ed42b8bc3e","source":{"kind":"arxiv","id":"2405.07595","version":1},"attestation_state":"computed","paper":{"title":"Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dehong Kong, Siyuan Liang, Wenqi Ren","submitted_at":"2024-05-13T09:56:57Z","abstract_excerpt":"Object detection techniques for Unmanned Aerial Vehicles (UAVs) rely on Deep Neural Networks (DNNs), which are vulnerable to adversarial attacks. Nonetheless, adversarial patches generated by existing algorithms in the UAV domain pay very little attention to the naturalness of adversarial patches. Moreover, imposing constraints directly on adversarial patches makes it difficult to generate patches that appear natural to the human eye while ensuring a high attack success rate. We notice that patches are natural looking when their overall color is consistent with the environment. Therefore, we p"},"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":"2405.07595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-13T09:56:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f6795e76a0b73223e1b2ab299a211c8d0abaa9903ef522bcdf8a659f0e47365c","abstract_canon_sha256":"9befc27c55394a120d0865857edc90f3cb8f4fca3b00eb82922864cb7ac2663d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:25.210498Z","signature_b64":"JgDkXLOqjwrwHw6yl8wXL21pFDRL4frAL2Cgn6vrQRQtZazOtu1CrxbYcZ0nsUL2BD/WFlRfr1BGBIVhpDT6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6d6f1e2dcd70d8a25f764e56e6a2735029a1019f06afd377430e9ed42b8bc3e","last_reissued_at":"2026-07-05T08:18:25.210125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:25.210125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dehong Kong, Siyuan Liang, Wenqi Ren","submitted_at":"2024-05-13T09:56:57Z","abstract_excerpt":"Object detection techniques for Unmanned Aerial Vehicles (UAVs) rely on Deep Neural Networks (DNNs), which are vulnerable to adversarial attacks. Nonetheless, adversarial patches generated by existing algorithms in the UAV domain pay very little attention to the naturalness of adversarial patches. Moreover, imposing constraints directly on adversarial patches makes it difficult to generate patches that appear natural to the human eye while ensuring a high attack success rate. We notice that patches are natural looking when their overall color is consistent with the environment. Therefore, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07595","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/2405.07595/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":"2405.07595","created_at":"2026-07-05T08:18:25.210179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.07595v1","created_at":"2026-07-05T08:18:25.210179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07595","created_at":"2026-07-05T08:18:25.210179+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3LPDYW424GY","created_at":"2026-07-05T08:18:25.210179+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3LPDYW424GYUJPX","created_at":"2026-07-05T08:18:25.210179+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3LPDYW4","created_at":"2026-07-05T08:18:25.210179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.18275","citing_title":"Visual Adversarial Attack on Vision-Language Models for Autonomous Driving","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04488","citing_title":"A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04630","citing_title":"Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3LPDYW424GYUJPXMTSW42RHGU","json":"https://pith.science/pith/Y3LPDYW424GYUJPXMTSW42RHGU.json","graph_json":"https://pith.science/api/pith-number/Y3LPDYW424GYUJPXMTSW42RHGU/graph.json","events_json":"https://pith.science/api/pith-number/Y3LPDYW424GYUJPXMTSW42RHGU/events.json","paper":"https://pith.science/paper/Y3LPDYW4"},"agent_actions":{"view_html":"https://pith.science/pith/Y3LPDYW424GYUJPXMTSW42RHGU","download_json":"https://pith.science/pith/Y3LPDYW424GYUJPXMTSW42RHGU.json","view_paper":"https://pith.science/paper/Y3LPDYW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.07595&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3LPDYW424GYUJPXMTSW42RHGU/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3LPDYW424GYUJPXMTSW42RHGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3LPDYW424GYUJPXMTSW42RHGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3LPDYW424GYUJPXMTSW42RHGU/action/storage_attestation","attest_author":"https://pith.science/pith/Y3LPDYW424GYUJPXMTSW42RHGU/action/author_attestation","sign_citation":"https://pith.science/pith/Y3LPDYW424GYUJPXMTSW42RHGU/action/citation_signature","submit_replication":"https://pith.science/pith/Y3LPDYW424GYUJPXMTSW42RHGU/action/replication_record"}},"created_at":"2026-07-05T08:18:25.210179+00:00","updated_at":"2026-07-05T08:18:25.210179+00:00"}