{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SQDGIV4JNIC26MF2HB6NBAZDFK","short_pith_number":"pith:SQDGIV4J","schema_version":"1.0","canonical_sha256":"94066457896a05af30ba387cd083232aa85fb673a5891fa3ed843bc92f703041","source":{"kind":"arxiv","id":"2111.11870","version":1},"attestation_state":"computed","paper":{"title":"DBIA: Data-free Backdoor Injection Attack against Transformer Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hualong Ma, Jiachen Zhou, Kai Chen, Peizhuo Lv, Ruigang Liang, Shengzhi Zhang, Yunfei Yang","submitted_at":"2021-11-22T08:13:51Z","abstract_excerpt":"Recently, transformer architecture has demonstrated its significance in both Natural Language Processing (NLP) and Computer Vision (CV) tasks. Though other network models are known to be vulnerable to the backdoor attack, which embeds triggers in the model and controls the model behavior when the triggers are presented, little is known whether such an attack is still valid on the transformer models and if so, whether it can be done in a more cost-efficient manner. In this paper, we propose DBIA, a novel data-free backdoor attack against the CV-oriented transformer networks, leveraging the inhe"},"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":"2111.11870","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-22T08:13:51Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"62802bb4bcc85877af31acf9305efaa00f8013b40acb05e4c88e77df8050bf4b","abstract_canon_sha256":"9b80e60cf2da0bb748304251d1d9d6359c154bb21ed45d94cc9d4bd36a894fa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:13.899562Z","signature_b64":"Rhej3M/AySd7m1B58DMfGqmp9sCcqUT9biaLfUhdYBdtAcaq+j8SQ8tCC8wf+a2VzTR3ncS2Aj6WZ14ZYlJvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94066457896a05af30ba387cd083232aa85fb673a5891fa3ed843bc92f703041","last_reissued_at":"2026-07-05T03:34:13.899052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:13.899052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DBIA: Data-free Backdoor Injection Attack against Transformer Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hualong Ma, Jiachen Zhou, Kai Chen, Peizhuo Lv, Ruigang Liang, Shengzhi Zhang, Yunfei Yang","submitted_at":"2021-11-22T08:13:51Z","abstract_excerpt":"Recently, transformer architecture has demonstrated its significance in both Natural Language Processing (NLP) and Computer Vision (CV) tasks. Though other network models are known to be vulnerable to the backdoor attack, which embeds triggers in the model and controls the model behavior when the triggers are presented, little is known whether such an attack is still valid on the transformer models and if so, whether it can be done in a more cost-efficient manner. In this paper, we propose DBIA, a novel data-free backdoor attack against the CV-oriented transformer networks, leveraging the inhe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11870","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/2111.11870/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":"2111.11870","created_at":"2026-07-05T03:34:13.899115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11870v1","created_at":"2026-07-05T03:34:13.899115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11870","created_at":"2026-07-05T03:34:13.899115+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQDGIV4JNIC2","created_at":"2026-07-05T03:34:13.899115+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQDGIV4JNIC26MF2","created_at":"2026-07-05T03:34:13.899115+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQDGIV4J","created_at":"2026-07-05T03:34:13.899115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.06149","citing_title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQDGIV4JNIC26MF2HB6NBAZDFK","json":"https://pith.science/pith/SQDGIV4JNIC26MF2HB6NBAZDFK.json","graph_json":"https://pith.science/api/pith-number/SQDGIV4JNIC26MF2HB6NBAZDFK/graph.json","events_json":"https://pith.science/api/pith-number/SQDGIV4JNIC26MF2HB6NBAZDFK/events.json","paper":"https://pith.science/paper/SQDGIV4J"},"agent_actions":{"view_html":"https://pith.science/pith/SQDGIV4JNIC26MF2HB6NBAZDFK","download_json":"https://pith.science/pith/SQDGIV4JNIC26MF2HB6NBAZDFK.json","view_paper":"https://pith.science/paper/SQDGIV4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11870&json=true","fetch_graph":"https://pith.science/api/pith-number/SQDGIV4JNIC26MF2HB6NBAZDFK/graph.json","fetch_events":"https://pith.science/api/pith-number/SQDGIV4JNIC26MF2HB6NBAZDFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQDGIV4JNIC26MF2HB6NBAZDFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQDGIV4JNIC26MF2HB6NBAZDFK/action/storage_attestation","attest_author":"https://pith.science/pith/SQDGIV4JNIC26MF2HB6NBAZDFK/action/author_attestation","sign_citation":"https://pith.science/pith/SQDGIV4JNIC26MF2HB6NBAZDFK/action/citation_signature","submit_replication":"https://pith.science/pith/SQDGIV4JNIC26MF2HB6NBAZDFK/action/replication_record"}},"created_at":"2026-07-05T03:34:13.899115+00:00","updated_at":"2026-07-05T03:34:13.899115+00:00"}