{"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/locally-differentially-private-federated","title":"Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses","arxiv_id":"2106.09779","date":"2021-06-17","proceeding":null,"authors":["Andrew Lowy","Meisam Razaviyayn"],"abstract":"This paper studies federated learning (FL)--especially cross-silo FL--with data from people who do not trust the server or other silos. In this setting, each silo (e.g. hospital) has data from different people (e.g. patients) and must maintain the privacy of each person's data (e.g. medical record), even if the server or other silos act as adversarial eavesdroppers. This requirement motivates the study of Inter-Silo Record-Level Differential Privacy (ISRL-DP), which requires silos' communications to satisfy record/item-level differential privacy (DP). ISRL-DP ensures that the data of each person (e.g. patient) in silo i (e.g. hospital i) cannot be leaked. ISRL-DP is different from well-studied privacy notions. Central and user-level DP assume that people trust the server/other silos. On the other end of the spectrum, local DP assumes that people do not trust anyone at all (even their own silo). Sitting between central and local DP, ISRL-DP makes the realistic assumption (in cross-silo FL) that people trust their own silo, but not the server or other silos. In this work, we provide tight (up to logarithms) upper and lower bounds for ISRL-DP FL with convex/strongly convex loss functions and homogeneous (i.i.d.) silo data. Remarkably, we show that similar bounds are attainable for smooth losses with arbitrary heterogeneous silo data distributions, via an accelerated ISRL-DP algorithm. We also provide tight upper and lower bounds for ISRL-DP federated empirical risk minimization, and use acceleration to attain the optimal bounds in fewer rounds of communication than the state-of-the-art. Finally, with a secure \"shuffler\" to anonymize silo messages (but without a trusted server), our algorithm attains the optimal central DP rates under more practical trust assumptions. Numerical experiments show favorable privacy-accuracy tradeoffs for our algorithm in classification and regression tasks.","url_abs":"https://arxiv.org/abs/2106.09779v10","url_pdf":"https://arxiv.org/pdf/2106.09779v10.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":"locally-differentially-private-federated","repo_url":"https://github.com/lowya/Locally-Differentially-Private-Federated-Learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"CC0-1.0"}},{"paper_slug":"locally-differentially-private-federated","repo_url":"https://github.com/lowya/private-federated-learning-without-a-trusted-server","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.09779","atlas_url":"https://app.syntology.ai/?focus=2106.09779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09779"}},"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/lowya/private-federated-learning-without-a-trusted-server","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lowya/Locally-Differentially-Private-Federated-Learning","reach":{"status":"ok","spdx":"CC0-1.0"}}],"summary":{"ran_honours":3,"ran_violates":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"61de19088914ff36","entry":"gradient","repo":"lowya/private-federated-learning-without-a-trusted-server","repo_kind":"official","path":"multiclasslogistic_convexFL_obesity.py","file_url":"https://github.com/lowya/private-federated-learning-without-a-trusted-server/blob/HEAD/multiclasslogistic_convexFL_obesity.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"61de19088914ff36"}},{"code_sha256_prefix":"aac4a4211640b600","entry":"logistic_loss","repo":"lowya/private-federated-learning-without-a-trusted-server","repo_kind":"official","path":"DP_FL_MNIST_logistic_FINAL.py","file_url":"https://github.com/lowya/private-federated-learning-without-a-trusted-server/blob/HEAD/DP_FL_MNIST_logistic_FINAL.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aac4a4211640b600"}},{"code_sha256_prefix":"738fe963944ac923","entry":"loss","repo":"lowya/private-federated-learning-without-a-trusted-server","repo_kind":"official","path":"multiclasslogistic_convexFL_obesity.py","file_url":"https://github.com/lowya/private-federated-learning-without-a-trusted-server/blob/HEAD/multiclasslogistic_convexFL_obesity.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"738fe963944ac923"}},{"code_sha256_prefix":"58eb8e19abd6d694","entry":"sigmoid","repo":"lowya/private-federated-learning-without-a-trusted-server","repo_kind":"official","path":"DP_FL_MNIST_logistic_FINAL.py","file_url":"https://github.com/lowya/private-federated-learning-without-a-trusted-server/blob/HEAD/DP_FL_MNIST_logistic_FINAL.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"58eb8e19abd6d694"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}