{"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/mitigating-the-backdoor-effect-for-multi-task","title":"Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace","arxiv_id":"2410.13910","date":"2024-10-17","proceeding":null,"authors":["Jinluan Yang","Anke Tang","Didi Zhu","Zhengyu Chen","Li Shen","Fei Wu"],"abstract":"Model merging has gained significant attention as a cost-effective approach to integrate multiple single-task fine-tuned models into a unified one that can perform well on multiple tasks. However, existing model merging techniques primarily focus on resolving conflicts between task-specific models, they often overlook potential security threats, particularly the risk of backdoor attacks in the open-source model ecosystem. In this paper, we first investigate the vulnerabilities of existing model merging methods to backdoor attacks, identifying two critical challenges: backdoor succession and backdoor transfer. To address these issues, we propose a novel Defense-Aware Merging (DAM) approach that simultaneously mitigates task interference and backdoor vulnerabilities. Specifically, DAM employs a meta-learning-based optimization method with dual masks to identify a shared and safety-aware subspace for model merging. These masks are alternately optimized: the Task-Shared mask identifies common beneficial parameters across tasks, aiming to preserve task-specific knowledge while reducing interference, while the Backdoor-Detection mask isolates potentially harmful parameters to neutralize security threats. This dual-mask design allows us to carefully balance the preservation of useful knowledge and the removal of potential vulnerabilities. Compared to existing merging methods, DAM achieves a more favorable balance between performance and security, reducing the attack success rate by 2-10 percentage points while sacrificing only about 1% in accuracy. Furthermore, DAM exhibits robust performance and broad applicability across various types of backdoor attacks and the number of compromised models involved in the merging process. Our codes and models are available at https://github.com/Yangjinluan/DAM.","url_abs":"https://arxiv.org/abs/2410.13910v2","url_pdf":"https://arxiv.org/pdf/2410.13910v2.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":"mitigating-the-backdoor-effect-for-multi-task","repo_url":"https://github.com/yangjinluan/dam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.13910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13910"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangjinluan/dam","reach":{"status":"ok"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"32cdbe419d673220","entry":"has_attr","repo":"yangjinluan/dam","repo_kind":"official","path":"fusion_bench/fusion_bench/models/parameter_dict.py","file_url":"https://github.com/yangjinluan/dam/blob/HEAD/fusion_bench/fusion_bench/models/parameter_dict.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"32cdbe419d673220"}},{"code_sha256_prefix":"76ee307172f085e2","entry":"load_gpt2_tokenizer","repo":"yangjinluan/dam","repo_kind":"official","path":"fusion_bench/fusion_bench/modelpool/huggingface_gpt2_classification.py","file_url":"https://github.com/yangjinluan/dam/blob/HEAD/fusion_bench/fusion_bench/modelpool/huggingface_gpt2_classification.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"76ee307172f085e2"}},{"code_sha256_prefix":"6866d2a6d69a1ecd","entry":"recombine_modeldict","repo":"yangjinluan/dam","repo_kind":"official","path":"fusion_bench/fusion_bench/method/model_recombination.py","file_url":"https://github.com/yangjinluan/dam/blob/HEAD/fusion_bench/fusion_bench/method/model_recombination.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6866d2a6d69a1ecd"}},{"code_sha256_prefix":"b5d44b089a2cdd0b","entry":"recombine_modellist","repo":"yangjinluan/dam","repo_kind":"official","path":"fusion_bench/fusion_bench/method/model_recombination.py","file_url":"https://github.com/yangjinluan/dam/blob/HEAD/fusion_bench/fusion_bench/method/model_recombination.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b5d44b089a2cdd0b"}},{"code_sha256_prefix":"3e6d09646a3092dc","entry":"recombine_state_dict","repo":"yangjinluan/dam","repo_kind":"official","path":"fusion_bench/fusion_bench/method/model_recombination.py","file_url":"https://github.com/yangjinluan/dam/blob/HEAD/fusion_bench/fusion_bench/method/model_recombination.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3e6d09646a3092dc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}