{"id":15039656,"url":"https://github.com/trusted-ai/adversarial-robustness-toolbox","last_synced_at":"2025-05-13T20:05:59.545Z","repository":{"id":37103006,"uuid":"125381318","full_name":"Trusted-AI/adversarial-robustness-toolbox","owner":"Trusted-AI","description":"Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams","archived":false,"fork":false,"pushed_at":"2025-05-05T07:37:35.000Z","size":640007,"stargazers_count":5234,"open_issues_count":34,"forks_count":1210,"subscribers_count":99,"default_branch":"main","last_synced_at":"2025-05-06T19:52:10.828Z","etag":null,"topics":["adversarial-attacks","adversarial-examples","adversarial-machine-learning","ai","artificial-intelligence","attack","blue-team","evasion","extraction","inference","machine-learning","poisoning","privacy","python","red-team","trusted-ai","trustworthy-ai"],"latest_commit_sha":null,"homepage":"https://adversarial-robustness-toolbox.readthedocs.io/en/latest/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Trusted-AI.png","metadata":{"files":{"readme":"README-cn.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":"AUTHORS","dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2018-03-15T14:40:43.000Z","updated_at":"2025-05-06T18:11:55.000Z","dependencies_parsed_at":"2023-10-14T23:20:38.321Z","dependency_job_id":"9daa2e85-4ad4-4e03-bee4-7b044bc808d5","html_url":"https://github.com/Trusted-AI/adversarial-robustness-toolbox","commit_stats":{"total_commits":9828,"total_committers":131,"mean_commits":75.02290076335878,"dds":0.6925111925111925,"last_synced_commit":"a62220fd28873f31bd6ad9c84ea8da10047c8d54"},"previous_names":["ibm/adversarial-robustness-toolbox"],"tags_count":64,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Trusted-AI%2Fadversarial-robustness-toolbox","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Trusted-AI%2Fadversarial-robustness-toolbox/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Trusted-AI%2Fadversarial-robustness-toolbox/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Trusted-AI%2Fadversarial-robustness-toolbox/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Trusted-AI","download_url":"https://codeload.github.com/Trusted-AI/adversarial-robustness-toolbox/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254020478,"owners_count":22000750,"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":["adversarial-attacks","adversarial-examples","adversarial-machine-learning","ai","artificial-intelligence","attack","blue-team","evasion","extraction","inference","machine-learning","poisoning","privacy","python","red-team","trusted-ai","trustworthy-ai"],"created_at":"2024-09-24T20:43:33.096Z","updated_at":"2025-05-13T20:05:54.526Z","avatar_url":"https://github.com/Trusted-AI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Adversarial Robustness Toolbox (ART) v1.18\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/images/art_lfai.png?raw=true\" width=\"467\" title=\"ART logo\"\u003e\n\u003c/p\u003e\n\u003cbr /\u003e\n\n![CodeQL](https://github.com/Trusted-AI/adversarial-robustness-toolbox/workflows/CodeQL/badge.svg)\n[![Documentation Status](https://readthedocs.org/projects/adversarial-robustness-toolbox/badge/?version=latest)](http://adversarial-robustness-toolbox.readthedocs.io/en/latest/?badge=latest)\n[![PyPI](https://badge.fury.io/py/adversarial-robustness-toolbox.svg)](https://badge.fury.io/py/adversarial-robustness-toolbox)\n[![codecov](https://codecov.io/gh/Trusted-AI/adversarial-robustness-toolbox/branch/main/graph/badge.svg)](https://codecov.io/gh/Trusted-AI/adversarial-robustness-toolbox)\n[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/adversarial-robustness-toolbox)](https://pypi.org/project/adversarial-robustness-toolbox/)\n[![slack-img](https://img.shields.io/badge/chat-on%20slack-yellow.svg)](https://ibm-art.slack.com/)\n[![Downloads](https://static.pepy.tech/badge/adversarial-robustness-toolbox)](https://pepy.tech/project/adversarial-robustness-toolbox)\n[![Downloads](https://static.pepy.tech/badge/adversarial-robustness-toolbox/month)](https://pepy.tech/project/adversarial-robustness-toolbox)\n[![CII Best Practices](https://bestpractices.coreinfrastructure.org/projects/5090/badge)](https://bestpractices.coreinfrastructure.org/projects/5090)\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/lfai/artwork/master/lfaidata-assets/lfaidata-project-badge/graduate/color/lfaidata-project-badge-graduate-color.png\" alt=\"LF AI \u0026 Data\" width=\"300\"/\u003e\n\u003c/p\u003e\n\n对抗性鲁棒性工具集（ART）是用于机器学习安全性的Python库。ART 由\n[Linux Foundation AI \u0026 Data Foundation](https://lfaidata.foundation) (LF AI \u0026 Data)。 ART提供的工具可\n帮助开发人员和研究人员针对以下方面捍卫和评估机器学习模型和应用程序：\n逃逸，数据污染，模型提取和推断的对抗性威胁。ART支持所有流行的机器学习框架\n（TensorFlow，Keras，PyTorch，MXNet，scikit-learn，XGBoost，LightGBM，CatBoost，GPy等），所有数据类型\n（图像，表格，音频，视频等）和机器学习任务（分类，物体检测，语音识别，\n生成模型，认证等）。\n\n## Adversarial Threats\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/images/adversarial_threats_attacker.png?raw=true\" width=\"400\" title=\"ART logo\"\u003e\n  \u003cimg src=\"docs/images/adversarial_threats_art.png?raw=true\" width=\"400\" title=\"ART logo\"\u003e\n\u003c/p\u003e\n\u003cbr /\u003e\n\n## ART for Red and Blue Teams (selection)\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/images/white_hat_blue_red.png?raw=true\" width=\"800\" title=\"ART Red and Blue Teams\"\u003e\n\u003c/p\u003e\n\u003cbr /\u003e\n\n## 学到更多\n\n| **[开始使用][get-started]**     | **[文献资料][documentation]**     | **[贡献][contributing]**           |\n|-------------------------------------|-------------------------------|-----------------------------------|\n| - [安装][installation]\u003cbr\u003e- [例子](examples/README.md)\u003cbr\u003e- [Notebooks](notebooks/README.md) | - [攻击][attacks]\u003cbr\u003e- [防御][defences]\u003cbr\u003e- [评估器][estimators]\u003cbr\u003e- [指标][metrics]\u003cbr\u003e- [技术文档](https://adversarial-robustness-toolbox.readthedocs.io) | - [Slack](https://ibm-art.slack.com), [邀请函](https://join.slack.com/t/ibm-art/shared_invite/enQtMzkyOTkyODE4NzM4LTA4NGQ1OTMxMzFmY2Q1MzE1NWI2MmEzN2FjNGNjOGVlODVkZDE0MjA1NTA4OGVkMjVkNmQ4MTY1NmMyOGM5YTg)\u003cbr\u003e- [贡献](CONTRIBUTING.md)\u003cbr\u003e- [路线图][roadmap]\u003cbr\u003e- [引用][citing] |\n\n[get-started]: https://github.com/Trusted-AI/adversarial-robustness-toolbox/wiki/Get-Started\n[attacks]: https://github.com/Trusted-AI/adversarial-robustness-toolbox/wiki/ART-Attacks\n[defences]: https://github.com/Trusted-AI/adversarial-robustness-toolbox/wiki/ART-Defences\n[estimators]: https://github.com/Trusted-AI/adversarial-robustness-toolbox/wiki/ART-Estimators\n[metrics]: https://github.com/Trusted-AI/adversarial-robustness-toolbox/wiki/ART-Metrics\n[contributing]: https://github.com/Trusted-AI/adversarial-robustness-toolbox/wiki/Contributing\n[documentation]: https://github.com/Trusted-AI/adversarial-robustness-toolbox/wiki/Documentation\n[installation]: https://github.com/Trusted-AI/adversarial-robustness-toolbox/wiki/Get-Started#setup\n[roadmap]: https://github.com/Trusted-AI/adversarial-robustness-toolbox/wiki/Roadmap\n[citing]: https://github.com/Trusted-AI/adversarial-robustness-toolbox/wiki/Contributing#citing-art\n\n该库正在不断开发中。欢迎反馈，错误报告和贡献！\n\n# 致谢\n\n本材料部分基于国防高级研究计划局（DARPA）支持的工作，合同编号HR001120C0013。\n本材料中表达的任何意见，发现和结论或建议均为作者的观点，并不一定反映国防高级研究计划局（DARPA）的观点。\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrusted-ai%2Fadversarial-robustness-toolbox","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftrusted-ai%2Fadversarial-robustness-toolbox","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrusted-ai%2Fadversarial-robustness-toolbox/lists"}