{"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/you-can-backdoor-personalized-federated","title":"You Can Backdoor Personalized Federated Learning","arxiv_id":"2307.15971","date":"2023-07-29","proceeding":null,"authors":["Tiandi Ye","Cen Chen","Yinggui Wang","Xiang Li","Ming Gao"],"abstract":"Existing research primarily focuses on backdoor attacks and defenses within the generic federated learning scenario, where all clients collaborate to train a single global model. A recent study conducted by Qin et al. (2023) marks the initial exploration of backdoor attacks within the personalized federated learning (pFL) scenario, where each client constructs a personalized model based on its local data. Notably, the study demonstrates that pFL methods with \\textit{parameter decoupling} can significantly enhance robustness against backdoor attacks. However, in this paper, we whistleblow that pFL methods with parameter decoupling are still vulnerable to backdoor attacks. The resistance of pFL methods with parameter decoupling is attributed to the heterogeneous classifiers between malicious clients and benign counterparts. We analyze two direct causes of the heterogeneous classifiers: (1) data heterogeneity inherently exists among clients and (2) poisoning by malicious clients further exacerbates the data heterogeneity. To address these issues, we propose a two-pronged attack method, BapFL, which comprises two simple yet effective strategies: (1) poisoning only the feature encoder while keeping the classifier fixed and (2) diversifying the classifier through noise introduction to simulate that of the benign clients. Extensive experiments on three benchmark datasets under varying conditions demonstrate the effectiveness of our proposed attack. Additionally, we evaluate the effectiveness of six widely used defense methods and find that BapFL still poses a significant threat even in the presence of the best defense, Multi-Krum. We hope to inspire further research on attack and defense strategies in pFL scenarios. The code is available at: https://github.com/BapFL/code.","url_abs":"https://arxiv.org/abs/2307.15971v2","url_pdf":"https://arxiv.org/pdf/2307.15971v2.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":"you-can-backdoor-personalized-federated","repo_url":"https://github.com/bapfl/code","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"backdoor-attack","task_name":"Backdoor Attack"},{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"personalized-federated-learning","task_name":"Personalized Federated Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.15971","atlas_url":"https://app.syntology.ai/?focus=2307.15971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15971"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bapfl/code","reach":{"status":"ok"}}],"summary":{"ran":6},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":6,"samples":[{"code_sha256_prefix":"7e608ae08522865c","entry":"avg_metric","repo":"bapfl/code","repo_kind":"official","path":"utils/set_md.py","file_url":"https://github.com/bapfl/code/blob/HEAD/utils/set_md.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":"7e608ae08522865c"}},{"code_sha256_prefix":"00d8f2684c594e42","entry":"clip_norm","repo":"bapfl/code","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/bapfl/code/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"00d8f2684c594e42"}},{"code_sha256_prefix":"32729b112d68b837","entry":"fed_average","repo":"bapfl/code","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/bapfl/code/blob/HEAD/utils/utils.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":"32729b112d68b837"}},{"code_sha256_prefix":"0d2cd350ec88e2cf","entry":"flatten_shared_parameters","repo":"bapfl/code","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/bapfl/code/blob/HEAD/utils/utils.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":"0d2cd350ec88e2cf"}},{"code_sha256_prefix":"69cb81ed8262cd92","entry":"make_layers","repo":"bapfl/code","repo_kind":"official","path":"models/Cifar10Net.py","file_url":"https://github.com/bapfl/code/blob/HEAD/models/Cifar10Net.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":"69cb81ed8262cd92"}},{"code_sha256_prefix":"9ef94bd9488b7ebe","entry":"vgg11","repo":"bapfl/code","repo_kind":"official","path":"models/Cifar10Net.py","file_url":"https://github.com/bapfl/code/blob/HEAD/models/Cifar10Net.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":"9ef94bd9488b7ebe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}