{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:777GECKWWR3P4IFVY35MLUMVVB","short_pith_number":"pith:777GECKW","schema_version":"1.0","canonical_sha256":"fffe620956b476fe20b5c6fac5d195a875dc1b13b4208b69fcbfedb8e8f755c7","source":{"kind":"arxiv","id":"2205.09592","version":1},"attestation_state":"computed","paper":{"title":"Transferable Physical Attack against Object Detection with Separable Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahao Qi, Kangcheng Bin, Ping Zhong, Wei Xue, Yichuang Zhang, Yongqian Li, Yu Zhang, Zhiqiang Gong","submitted_at":"2022-05-19T14:34:55Z","abstract_excerpt":"Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability to unseen models, thus leading to the poor performance of black-box attack.In this paper, we put forward a novel method of generating physically realizable adversarial camouflage to achieve transferable attack against detection models. More specifically, we first introduce multi-scale attention maps based on detection models to capture features of objects wit"},"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":"2205.09592","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-19T14:34:55Z","cross_cats_sorted":[],"title_canon_sha256":"a2bdd51f453088a61148bbf4f8ed1192b0fdb7eaefccd98ed397834195d709cf","abstract_canon_sha256":"9fb66bc85220bafc32e6787330a7af120f3663f4bafa9430e65de343a527553c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:46.519104Z","signature_b64":"42D+fqYJrFmUrPN0W53Z5Mk5ghb9P0pzItFs8DW1E3ERsgipeFN7T3HuypoK/XfjRnNc+f7iGw4+Y74E41uQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fffe620956b476fe20b5c6fac5d195a875dc1b13b4208b69fcbfedb8e8f755c7","last_reissued_at":"2026-07-05T04:24:46.518710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:46.518710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferable Physical Attack against Object Detection with Separable Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahao Qi, Kangcheng Bin, Ping Zhong, Wei Xue, Yichuang Zhang, Yongqian Li, Yu Zhang, Zhiqiang Gong","submitted_at":"2022-05-19T14:34:55Z","abstract_excerpt":"Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability to unseen models, thus leading to the poor performance of black-box attack.In this paper, we put forward a novel method of generating physically realizable adversarial camouflage to achieve transferable attack against detection models. More specifically, we first introduce multi-scale attention maps based on detection models to capture features of objects wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09592","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/2205.09592/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":"2205.09592","created_at":"2026-07-05T04:24:46.518772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.09592v1","created_at":"2026-07-05T04:24:46.518772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09592","created_at":"2026-07-05T04:24:46.518772+00:00"},{"alias_kind":"pith_short_12","alias_value":"777GECKWWR3P","created_at":"2026-07-05T04:24:46.518772+00:00"},{"alias_kind":"pith_short_16","alias_value":"777GECKWWR3P4IFV","created_at":"2026-07-05T04:24:46.518772+00:00"},{"alias_kind":"pith_short_8","alias_value":"777GECKW","created_at":"2026-07-05T04:24:46.518772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18718","citing_title":"Evaluating the Adversarial Robustness of Detection Transformers","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/777GECKWWR3P4IFVY35MLUMVVB","json":"https://pith.science/pith/777GECKWWR3P4IFVY35MLUMVVB.json","graph_json":"https://pith.science/api/pith-number/777GECKWWR3P4IFVY35MLUMVVB/graph.json","events_json":"https://pith.science/api/pith-number/777GECKWWR3P4IFVY35MLUMVVB/events.json","paper":"https://pith.science/paper/777GECKW"},"agent_actions":{"view_html":"https://pith.science/pith/777GECKWWR3P4IFVY35MLUMVVB","download_json":"https://pith.science/pith/777GECKWWR3P4IFVY35MLUMVVB.json","view_paper":"https://pith.science/paper/777GECKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.09592&json=true","fetch_graph":"https://pith.science/api/pith-number/777GECKWWR3P4IFVY35MLUMVVB/graph.json","fetch_events":"https://pith.science/api/pith-number/777GECKWWR3P4IFVY35MLUMVVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/777GECKWWR3P4IFVY35MLUMVVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/777GECKWWR3P4IFVY35MLUMVVB/action/storage_attestation","attest_author":"https://pith.science/pith/777GECKWWR3P4IFVY35MLUMVVB/action/author_attestation","sign_citation":"https://pith.science/pith/777GECKWWR3P4IFVY35MLUMVVB/action/citation_signature","submit_replication":"https://pith.science/pith/777GECKWWR3P4IFVY35MLUMVVB/action/replication_record"}},"created_at":"2026-07-05T04:24:46.518772+00:00","updated_at":"2026-07-05T04:24:46.518772+00:00"}