{"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/auditing-differentially-private-machine","title":"Auditing Differentially Private Machine Learning: How Private is Private SGD?","arxiv_id":"2006.07709","date":"2020-06-13","proceeding":"NeurIPS 2020 12","authors":["Matthew Jagielski","Jonathan Ullman","Alina Oprea"],"abstract":"We investigate whether Differentially Private SGD offers better privacy in practice than what is guaranteed by its state-of-the-art analysis. We do so via novel data poisoning attacks, which we show correspond to realistic privacy attacks. While previous work (Ma et al., arXiv 2019) proposed this connection between differential privacy and data poisoning as a defense against data poisoning, our use as a tool for understanding the privacy of a specific mechanism is new. More generally, our work takes a quantitative, empirical approach to understanding the privacy afforded by specific implementations of differentially private algorithms that we believe has the potential to complement and influence analytical work on differential privacy.","url_abs":"https://arxiv.org/abs/2006.07709v1","url_pdf":"https://arxiv.org/pdf/2006.07709v1.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":"auditing-differentially-private-machine","repo_url":"https://github.com/jagielski/auditing-dpsgd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"art-analysis","task_name":"Art Analysis"},{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"data-poisoning","task_name":"Data Poisoning"}],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.07709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07709"}},"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/jagielski/auditing-dpsgd","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"3d53bb923bd2a274","entry":"backdoor_train","repo":"jagielski/auditing-dpsgd","repo_kind":"official","path":"code/audit.py","file_url":"https://github.com/jagielski/auditing-dpsgd/blob/HEAD/code/audit.py","link_basis":"first_harvest_node","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":"3d53bb923bd2a274"}},{"code_sha256_prefix":"d314d09dc17a785f","entry":"bkd_find_thresh","repo":"jagielski/auditing-dpsgd","repo_kind":"official","path":"code/bkd_parser.py","file_url":"https://github.com/jagielski/auditing-dpsgd/blob/HEAD/code/bkd_parser.py","link_basis":"first_harvest_node","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":"d314d09dc17a785f"}},{"code_sha256_prefix":"15892840c1537e01","entry":"bkd_get_eps","repo":"jagielski/auditing-dpsgd","repo_kind":"official","path":"code/bkd_parser.py","file_url":"https://github.com/jagielski/auditing-dpsgd/blob/HEAD/code/bkd_parser.py","link_basis":"first_harvest_node","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":"15892840c1537e01"}},{"code_sha256_prefix":"86f540150b92a2dc","entry":"build_model","repo":"jagielski/auditing-dpsgd","repo_kind":"official","path":"code/audit.py","file_url":"https://github.com/jagielski/auditing-dpsgd/blob/HEAD/code/audit.py","link_basis":"first_harvest_node","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":"86f540150b92a2dc"}},{"code_sha256_prefix":"3df71a2c373df03e","entry":"clopper_pearson","repo":"jagielski/auditing-dpsgd","repo_kind":"official","path":"code/bkd_parser.py","file_url":"https://github.com/jagielski/auditing-dpsgd/blob/HEAD/code/bkd_parser.py","link_basis":"first_harvest_node","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":"3df71a2c373df03e"}},{"code_sha256_prefix":"814bbbf2838c3144","entry":"get_cfg","repo":"jagielski/auditing-dpsgd","repo_kind":"official","path":"code/make_nps.py","file_url":"https://github.com/jagielski/auditing-dpsgd/blob/HEAD/code/make_nps.py","link_basis":"first_harvest_node","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":"814bbbf2838c3144"}},{"code_sha256_prefix":"cb7f2c6a458b26ab","entry":"parse_name","repo":"jagielski/auditing-dpsgd","repo_kind":"official","path":"code/combine_files.py","file_url":"https://github.com/jagielski/auditing-dpsgd/blob/HEAD/code/combine_files.py","link_basis":"first_harvest_node","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":"cb7f2c6a458b26ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}