{"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/deep-learning-with-gaussian-differential","title":"Deep Learning with Gaussian Differential Privacy","arxiv_id":"1911.11607","date":"2019-11-26","proceeding":null,"authors":["Zhiqi Bu","Jinshuo Dong","Qi Long","Weijie J. Su"],"abstract":"Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train neural networks subject to privacy constraints that are specified by differential privacy or its divergence-based relaxations. These privacy definitions, however, have weaknesses in handling certain important primitives (composition and subsampling), thereby giving loose or complicated privacy analyses of training neural networks. In this paper, we consider a recently proposed privacy definition termed \\textit{$f$-differential privacy} [18] for a refined privacy analysis of training neural networks. Leveraging the appealing properties of $f$-differential privacy in handling composition and subsampling, this paper derives analytically tractable expressions for the privacy guarantees of both stochastic gradient descent and Adam used in training deep neural networks, without the need of developing sophisticated techniques as [3] did. Our results demonstrate that the $f$-differential privacy framework allows for a new privacy analysis that improves on the prior analysis~[3], which in turn suggests tuning certain parameters of neural networks for a better prediction accuracy without violating the privacy budget. These theoretically derived improvements are confirmed by our experiments in a range of tasks in image classification, text classification, and recommender systems. Python code to calculate the privacy cost for these experiments is publicly available in the \\texttt{TensorFlow Privacy} library.","url_abs":"https://arxiv.org/abs/1911.11607v3","url_pdf":"https://arxiv.org/pdf/1911.11607v3.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":"deep-learning-with-gaussian-differential","repo_url":"https://github.com/woodyx218/Deep-Learning-with-GDP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-learning-with-gaussian-differential","repo_url":"https://github.com/woodyx218/Deep-Learning-with-GDP-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-learning-with-gaussian-differential","repo_url":"https://github.com/woodyx218/Deep-Learning-with-GDP-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"adam","method_name":"Adam"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.11607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.11607"}},"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/woodyx218/Deep-Learning-with-GDP","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/woodyx218/Deep-Learning-with-GDP-Tensorflow","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/woodyx218/Deep-Learning-with-GDP-Pytorch","reach":{"status":"ok"}}],"summary":{"ran_violates":3,"unverified":1},"by_repo_kind":{"listed":{"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":4,"samples":[{"code_sha256_prefix":"985d1d3378bbbe97","entry":"compute_muP","repo":"woodyx218/Deep-Learning-with-GDP-Tensorflow","repo_kind":"listed","path":"gdp_accountant.py","file_url":"https://github.com/woodyx218/Deep-Learning-with-GDP-Tensorflow/blob/HEAD/gdp_accountant.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"985d1d3378bbbe97"}},{"code_sha256_prefix":"b9512c1b0601c501","entry":"compute_muU","repo":"woodyx218/Deep-Learning-with-GDP-Tensorflow","repo_kind":"listed","path":"gdp_accountant.py","file_url":"https://github.com/woodyx218/Deep-Learning-with-GDP-Tensorflow/blob/HEAD/gdp_accountant.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b9512c1b0601c501"}},{"code_sha256_prefix":"4714ee287d2fc5bc","entry":"delta_eps_mu","repo":"woodyx218/Deep-Learning-with-GDP-Tensorflow","repo_kind":"listed","path":"gdp_accountant.py","file_url":"https://github.com/woodyx218/Deep-Learning-with-GDP-Tensorflow/blob/HEAD/gdp_accountant.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4714ee287d2fc5bc"}},{"code_sha256_prefix":"0084ec1c2df6dc92","entry":"test","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"0084ec1c2df6dc92"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}