{"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/crfl-certifiably-robust-federated-learning","title":"CRFL: Certifiably Robust Federated Learning against Backdoor Attacks","arxiv_id":"2106.08283","date":"2021-06-15","proceeding":null,"authors":["Chulin Xie","Minghao Chen","Pin-Yu Chen","Bo Li"],"abstract":"Federated Learning (FL) as a distributed learning paradigm that aggregates information from diverse clients to train a shared global model, has demonstrated great success. However, malicious clients can perform poisoning attacks and model replacement to introduce backdoors into the trained global model. Although there have been intensive studies designing robust aggregation methods and empirical robust federated training protocols against backdoors, existing approaches lack robustness certification. This paper provides the first general framework, Certifiably Robust Federated Learning (CRFL), to train certifiably robust FL models against backdoors. Our method exploits clipping and smoothing on model parameters to control the global model smoothness, which yields a sample-wise robustness certification on backdoors with limited magnitude. Our certification also specifies the relation to federated learning parameters, such as poisoning ratio on instance level, number of attackers, and training iterations. Practically, we conduct comprehensive experiments across a range of federated datasets, and provide the first benchmark for certified robustness against backdoor attacks in federated learning. Our code is available at https://github.com/AI-secure/CRFL.","url_abs":"https://arxiv.org/abs/2106.08283v1","url_pdf":"https://arxiv.org/pdf/2106.08283v1.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":"crfl-certifiably-robust-federated-learning","repo_url":"https://github.com/AI-secure/CRFL","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":{"atlas_url":"https://app.syntology.ai/?focus=2106.08283","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08283"}},"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":"deterministic:regex_extraction","url":"https://github.com/AI-secure/CRFL","reach":null}],"summary":{"ran_fixture":1,"ran_honours":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"d348bb1439439260","entry":"cal_prob_bound","repo":"AI-secure/CRFL","repo_kind":"official","path":"certify_mnist.py","file_url":"https://github.com/AI-secure/CRFL/blob/HEAD/certify_mnist.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d348bb1439439260"}},{"code_sha256_prefix":"4d7f485df31b3c02","entry":"eval_model","repo":"AI-secure/CRFL","repo_kind":"official","path":"smooth_mnist.py","file_url":"https://github.com/AI-secure/CRFL/blob/HEAD/smooth_mnist.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":"4d7f485df31b3c02"}},{"code_sha256_prefix":"de98333ec8edf7cf","entry":"probability_estimation","repo":"AI-secure/CRFL","repo_kind":"official","path":"smooth_mnist.py","file_url":"https://github.com/AI-secure/CRFL/blob/HEAD/smooth_mnist.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"de98333ec8edf7cf"}},{"code_sha256_prefix":"78325824cb26fc1b","entry":"certify","repo":"AI-secure/CRFL","repo_kind":"official","path":"certify_mnist.py","file_url":"https://github.com/AI-secure/CRFL/blob/HEAD/certify_mnist.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"78325824cb26fc1b"}},{"code_sha256_prefix":"9555552656525d17","entry":"dp_noise","repo":"AI-secure/CRFL","repo_kind":"official","path":"smooth_mnist.py","file_url":"https://github.com/AI-secure/CRFL/blob/HEAD/smooth_mnist.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9555552656525d17"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}