{"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/achieving-byzantine-resilient-federated","title":"Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregation","arxiv_id":"2409.01435","date":"2024-09-02","proceeding":null,"authors":["Jiahao Xu","Zikai Zhang","Rui Hu"],"abstract":"Federated Learning (FL) enables multiple clients to collaboratively train a model without sharing their local data. Yet the FL system is vulnerable to well-designed Byzantine attacks, which aim to disrupt the model training process by uploading malicious model updates. Existing robust aggregation rule-based defense methods overlook the diversity of magnitude and direction across different layers of the model updates, resulting in limited robustness performance, particularly in non-IID settings. To address these challenges, we propose the Layer-Adaptive Sparsified Model Aggregation (LASA) approach, which combines pre-aggregation sparsification with layer-wise adaptive aggregation to improve robustness. Specifically, LASA includes a pre-aggregation sparsification module that sparsifies updates from each client before aggregation, reducing the impact of malicious parameters and minimizing the interference from less important parameters for the subsequent filtering process. Based on sparsified updates, a layer-wise adaptive filter then adaptively selects benign layers using both magnitude and direction metrics across all clients for aggregation. We provide the detailed theoretical robustness analysis of LASA and the resilience analysis for the FL integrated with LASA. Extensive experiments are conducted on various IID and non-IID datasets. The numerical results demonstrate the effectiveness of LASA. Code is available at \\url{https://github.com/JiiahaoXU/LASA}.","url_abs":"https://arxiv.org/abs/2409.01435v1","url_pdf":"https://arxiv.org/pdf/2409.01435v1.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":"achieving-byzantine-resilient-federated","repo_url":"https://github.com/jiiahaoxu/lasa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2409.01435","atlas_url":"https://app.syntology.ai/?focus=2409.01435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.01435"}},"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/jiiahaoxu/lasa","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"c3ac56d9a80cafd1","entry":"parameters_dict_to_vector_flt","repo":"jiiahaoxu/lasa","repo_kind":"official","path":"algorithms/defense/lasa.py","file_url":"https://github.com/jiiahaoxu/lasa/blob/HEAD/algorithms/defense/lasa.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c3ac56d9a80cafd1"}},{"code_sha256_prefix":"891977b6cd73a3c7","entry":"topk","repo":"jiiahaoxu/lasa","repo_kind":"official","path":"algorithms/defense/lasa.py","file_url":"https://github.com/jiiahaoxu/lasa/blob/HEAD/algorithms/defense/lasa.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"891977b6cd73a3c7"}},{"code_sha256_prefix":"a9c36cb9479870b7","entry":"vector_to_net_dict","repo":"jiiahaoxu/lasa","repo_kind":"official","path":"algorithms/defense/lasa.py","file_url":"https://github.com/jiiahaoxu/lasa/blob/HEAD/algorithms/defense/lasa.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a9c36cb9479870b7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}