{"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/bayesian-estimation-of-differential-privacy","title":"Bayesian Estimation of Differential Privacy","arxiv_id":"2206.05199","date":"2022-06-10","proceeding":null,"authors":["Santiago Zanella-Béguelin","Lukas Wutschitz","Shruti Tople","Ahmed Salem","Victor Rühle","Andrew Paverd","Mohammad Naseri","Boris Köpf","Daniel Jones"],"abstract":"Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that such algorithms guarantee in theory and the protection they afford in practice. An emerging strand of work empirically estimates the protection afforded by differentially private training as a confidence interval for the privacy budget $\\varepsilon$ spent on training a model. Existing approaches derive confidence intervals for $\\varepsilon$ from confidence intervals for the false positive and false negative rates of membership inference attacks. Unfortunately, obtaining narrow high-confidence intervals for $\\epsilon$ using this method requires an impractically large sample size and training as many models as samples. We propose a novel Bayesian method that greatly reduces sample size, and adapt and validate a heuristic to draw more than one sample per trained model. Our Bayesian method exploits the hypothesis testing interpretation of differential privacy to obtain a posterior for $\\varepsilon$ (not just a confidence interval) from the joint posterior of the false positive and false negative rates of membership inference attacks. For the same sample size and confidence, we derive confidence intervals for $\\varepsilon$ around 40% narrower than prior work. The heuristic, which we adapt from label-only DP, can be used to further reduce the number of trained models needed to get enough samples by up to 2 orders of magnitude.","url_abs":"https://arxiv.org/abs/2206.05199v2","url_pdf":"https://arxiv.org/pdf/2206.05199v2.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":"bayesian-estimation-of-differential-privacy","repo_url":"https://github.com/microsoft/responsible-ai-toolbox-privacy","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2206.05199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05199"}},"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/microsoft/responsible-ai-toolbox-privacy","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"1442dde03a551ded","entry":"bound_membership_advantage","repo":"microsoft/responsible-ai-toolbox-privacy","repo_kind":"official","path":"privacy_estimates/utils.py","file_url":"https://github.com/microsoft/responsible-ai-toolbox-privacy/blob/HEAD/privacy_estimates/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1442dde03a551ded"}},{"code_sha256_prefix":"5fef3b5a5bb5e535","entry":"privacy_boundary_hi","repo":"microsoft/responsible-ai-toolbox-privacy","repo_kind":"official","path":"privacy_estimates/privacy_region.py","file_url":"https://github.com/microsoft/responsible-ai-toolbox-privacy/blob/HEAD/privacy_estimates/privacy_region.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5fef3b5a5bb5e535"}},{"code_sha256_prefix":"a57116687035a0ea","entry":"privacy_boundary_lo","repo":"microsoft/responsible-ai-toolbox-privacy","repo_kind":"official","path":"privacy_estimates/privacy_region.py","file_url":"https://github.com/microsoft/responsible-ai-toolbox-privacy/blob/HEAD/privacy_estimates/privacy_region.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a57116687035a0ea"}},{"code_sha256_prefix":"6e2dd6986553f8fd","entry":"privacy_boundary_normal_lo","repo":"microsoft/responsible-ai-toolbox-privacy","repo_kind":"official","path":"privacy_estimates/privacy_region.py","file_url":"https://github.com/microsoft/responsible-ai-toolbox-privacy/blob/HEAD/privacy_estimates/privacy_region.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e2dd6986553f8fd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}