{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/eliminating-backdoor-triggers-for-deep-neural","title":"Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation","arxiv_id":"2204.09975","date":"2022-04-21","proceeding":null,"authors":["Jun Xia","Ting Wang","Jiepin Ding","Xian Wei","Mingsong Chen"],"abstract":"Due to the prosperity of Artificial Intelligence (AI) techniques, more and more backdoors are designed by adversaries to attack Deep Neural Networks (DNNs).Although the state-of-the-art method Neural Attention Distillation (NAD) can effectively erase backdoor triggers from DNNs, it still suffers from non-negligible Attack Success Rate (ASR) together with lowered classification ACCuracy (ACC), since NAD focuses on backdoor defense using attention features (i.e., attention maps) of the same order. In this paper, we introduce a novel backdoor defense framework named Attention Relation Graph Distillation (ARGD), which fully explores the correlation among attention features with different orders using our proposed Attention Relation Graphs (ARGs). Based on the alignment of ARGs between both teacher and student models during knowledge distillation, ARGD can eradicate more backdoor triggers than NAD. Comprehensive experimental results show that, against six latest backdoor attacks, ARGD outperforms NAD by up to 94.85% reduction in ASR, while ACC can be improved by up to 3.23%.","url_abs":"https://arxiv.org/abs/2204.09975v2","url_pdf":"https://arxiv.org/pdf/2204.09975v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"eliminating-backdoor-triggers-for-deep-neural","repo_url":"https://github.com/BililiCode/ARGD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"backdoor-defense","task_name":"backdoor defense"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.09975","atlas_url":"https://app.syntology.ai/?focus=2204.09975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.09975"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/BililiCode/ARGD","reach":null}],"summary":{"ran":7},"by_repo_kind":{"official":{"samples":7,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"76e004c45f382256","entry":"ARGD","repo":"BililiCode/ARGD","repo_kind":"official","path":"riman_distance.py","file_url":"https://github.com/BililiCode/ARGD/blob/HEAD/riman_distance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"76e004c45f382256"}},{"code_sha256_prefix":"afe2bae22c072ae4","entry":"AT","repo":"BililiCode/ARGD","repo_kind":"official","path":"riman_distance.py","file_url":"https://github.com/BililiCode/ARGD/blob/HEAD/riman_distance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"afe2bae22c072ae4"}},{"code_sha256_prefix":"d6ce78123dac409c","entry":"Attention","repo":"BililiCode/ARGD","repo_kind":"official","path":"riman_distance.py","file_url":"https://github.com/BililiCode/ARGD/blob/HEAD/riman_distance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d6ce78123dac409c"}},{"code_sha256_prefix":"b4271d528cbcd565","entry":"LinearTransformStudent","repo":"BililiCode/ARGD","repo_kind":"official","path":"riman_distance.py","file_url":"https://github.com/BililiCode/ARGD/blob/HEAD/riman_distance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b4271d528cbcd565"}},{"code_sha256_prefix":"4583f0c50e0a261b","entry":"LinearTransformTeacher","repo":"BililiCode/ARGD","repo_kind":"official","path":"riman_distance.py","file_url":"https://github.com/BililiCode/ARGD/blob/HEAD/riman_distance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4583f0c50e0a261b"}},{"code_sha256_prefix":"4b0418b752234950","entry":"Sample","repo":"BililiCode/ARGD","repo_kind":"official","path":"riman_distance.py","file_url":"https://github.com/BililiCode/ARGD/blob/HEAD/riman_distance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b0418b752234950"}},{"code_sha256_prefix":"0faf01c20c285b2d","entry":"nn_bn_relu","repo":"BililiCode/ARGD","repo_kind":"official","path":"riman_distance.py","file_url":"https://github.com/BililiCode/ARGD/blob/HEAD/riman_distance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0faf01c20c285b2d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}