{"id":23384857,"url":"https://github.com/sap-archive/security-research-differentially-private-generative-models","last_synced_at":"2025-04-11T02:36:07.802Z","repository":{"id":52606575,"uuid":"203673795","full_name":"SAP-archive/security-research-differentially-private-generative-models","owner":"SAP-archive","description":"SAP Security research sample code and tutorials for generating differentially private synthetic datasets using generative deep learning models","archived":false,"fork":false,"pushed_at":"2024-03-07T16:38:28.000Z","size":903,"stargazers_count":23,"open_issues_count":9,"forks_count":11,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-03-25T00:11:13.258Z","etag":null,"topics":["dp-gans","dp-vae","sample","sample-code","security"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SAP-archive.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-08-21T22:33:31.000Z","updated_at":"2024-08-08T19:04:32.000Z","dependencies_parsed_at":"2024-12-21T23:30:31.162Z","dependency_job_id":"79db2aba-0a57-4f69-864e-958f30cd0394","html_url":"https://github.com/SAP-archive/security-research-differentially-private-generative-models","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SAP-archive%2Fsecurity-research-differentially-private-generative-models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SAP-archive%2Fsecurity-research-differentially-private-generative-models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SAP-archive%2Fsecurity-research-differentially-private-generative-models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SAP-archive%2Fsecurity-research-differentially-private-generative-models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SAP-archive","download_url":"https://codeload.github.com/SAP-archive/security-research-differentially-private-generative-models/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248330214,"owners_count":21085664,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["dp-gans","dp-vae","sample","sample-code","security"],"created_at":"2024-12-21T23:30:18.273Z","updated_at":"2025-04-11T02:36:07.794Z","avatar_url":"https://github.com/SAP-archive.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003c!--\r\nSPDX-FileCopyrightText: 2020 SAP SE\r\n\r\nSPDX-License-Identifier: Apache-2.0\r\n--\u003e\r\n\r\n![](https://img.shields.io/badge/STATUS-NOT%20CURRENTLY%20MAINTAINED-red.svg?longCache=true\u0026style=flat)\r\n\r\n# Important Notice\r\nThis public repository is read-only and no longer maintained. For the latest sample code repositories, visit the [SAP Samples](https://github.com/SAP-samples) organization.\r\n\r\n# Differentially Private Generative Models\r\n\r\n[![REUSE status](https://api.reuse.software/badge/github.com/SAP-samples/security-research-differentially-private-generative-models)](https://api.reuse.software/info/github.com/SAP-samples/security-research-differentially-private-generative-models)\r\n\r\n## Description:\r\nThis repository explains how generative models can be used in combination with differential privacy to synthetize feature-rich realistic categorical datasets in a privacy preserving manner. It brings two jupyter notebooks for dp-GANs (differentially-private Generative Adversarial Networks) and dp-VAE (Variational Autoencoder) to generate new data in a differetnial private mode. The code allows to quickly generate new dataset (incl. numerical features) in private or public mode. dp_SGD and dp_Adam optimizers from tensowflow/ privacy library (https://github.com/tensorflow/privacy) are used these models. \r\n\r\n## Requirements\r\n- [Python](https://www.python.org/)\r\n- [Jupyter](https://jupyter.org/)\r\n- [Tensorflow](https://github.com/tensorflow)\r\n- Pandas, keras, and more see the notebooks import sections\r\n- [H2O AutoML](http://docs.h2o.ai/h2o/latest-stable/h2o-docs/automl.html)\r\n- Check further dependencies in the Jupyter notebooks Tutorial_dp-GAN.ipynb and Tutorial_dp-VAE.ipynb\r\n\r\n## Download the tensorflow privacy project\r\n1. Clone Tensorflow privacy into this project repository :\r\n```\r\ngit clone https://github.com/tensorflow/privacy\r\n\r\ncd privacy\r\npip install -e .\r\n```\r\n\r\n\r\n2. Open the notebooks in Jupyter and run them\r\n\r\n\r\n## Authors / Contributors\r\n\r\n - Lyudmylla Dymytrova\r\n - Lorenzo Frigerio\r\n - Anderson Santana de Oliveira\r\n \r\n## Known Issues\r\nNo issues known\r\n\r\n\r\n## How to obtain support\r\nThis project is provided \"as-is\" and any bug reports are not guaranteed to be fixed.\r\n\r\n\r\n## Citations\r\nIf you use this code in your research,\r\nplease cite:\r\n\r\n```\r\n@article{DBLP:journals/corr/abs-1901-02477,\r\n  author    = {Lorenzo Frigerio and\r\n               Anderson Santana de Oliveira and\r\n               Laurent Gomez and\r\n               Patrick Duverger},\r\n  title     = {Differentially Private Generative Adversarial Networks for Time Series,\r\n               Continuous, and Discrete Open Data},\r\n  journal   = {CoRR},\r\n  volume    = {abs/1901.02477},\r\n  year      = {2019},\r\n  url       = {http://arxiv.org/abs/1901.02477},\r\n  archivePrefix = {arXiv},\r\n  eprint    = {1901.02477},\r\n  timestamp = {Fri, 01 Feb 2019 13:39:59 +0100},\r\n  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1901-02477},\r\n  bibsource = {dblp computer science bibliography, https://dblp.org}\r\n}\r\n```\r\n\r\n## References\r\n- [1] Lorenzo Frigerio, Anderson Santana de Oliveira, Laurent Gomez, Patrick Duverger:\r\nDifferentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data. CoRR abs/1901.02477 (2019). https://arxiv.org/abs/1901.02477\r\n\r\n\r\n## License\r\nCopyright (c) 2020 SAP SE or an SAP affiliate company. All rights reserved.\r\nThis project is licensed under the Apache Software License, version 2.0 except as noted otherwise in the [LICENSE](LICENSES/Apache-2.0.txt) file.\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsap-archive%2Fsecurity-research-differentially-private-generative-models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsap-archive%2Fsecurity-research-differentially-private-generative-models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsap-archive%2Fsecurity-research-differentially-private-generative-models/lists"}