[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-9776":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":15,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":43,"readmeContent":44,"aiSummary":45,"trendingCount":16,"starSnapshotCount":16,"syncStatus":46,"lastSyncTime":47,"discoverSource":48},9776,"adversarial-robustness-toolbox","Trusted-AI\u002Fadversarial-robustness-toolbox","Trusted-AI","Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams","https:\u002F\u002Fadversarial-robustness-toolbox.readthedocs.io\u002Fen\u002Flatest\u002F",null,"Python",6034,1321,101,4,0,15,54,16,86.26,"MIT License",false,"main",true,[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"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","2026-06-12 04:00:46","# Adversarial Robustness Toolbox (ART) v1.20\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002FTrusted-AI\u002Fadversarial-robustness-toolbox\u002Fmain\u002Fdocs\u002Fimages\u002Fart_lfai.png\" width=\"467\" title=\"ART logo\">\n\u003C\u002Fp>\n\u003Cbr \u002F>\n\n![CodeQL](https:\u002F\u002Fgithub.com\u002FTrusted-AI\u002Fadversarial-robustness-toolbox\u002Fworkflows\u002FCodeQL\u002Fbadge.svg)\n[![Documentation Status](https:\u002F\u002Freadthedocs.org\u002Fprojects\u002Fadversarial-robustness-toolbox\u002Fbadge\u002F?version=latest)](http:\u002F\u002Fadversarial-robustness-toolbox.readthedocs.io\u002Fen\u002Flatest\u002F?badge=latest)\n[![PyPI](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fadversarial-robustness-toolbox.svg)](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fadversarial-robustness-toolbox)\n[![codecov](https:\u002F\u002Fcodecov.io\u002Fgh\u002FTrusted-AI\u002Fadversarial-robustness-toolbox\u002Fbranch\u002Fmain\u002Fgraph\u002Fbadge.svg)](https:\u002F\u002Fcodecov.io\u002Fgh\u002FTrusted-AI\u002Fadversarial-robustness-toolbox)\n[![Code style: black](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcode%20style-black-000000.svg)](https:\u002F\u002Fgithub.com\u002Fpsf\u002Fblack)\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT)\n[![PyPI - Python Version](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Fadversarial-robustness-toolbox)](https:\u002F\u002Fpypi.org\u002Fproject\u002Fadversarial-robustness-toolbox\u002F)\n[![slack-img](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fchat-on%20slack-yellow.svg)](https:\u002F\u002Fibm-art.slack.com\u002F)\n[![Downloads](https:\u002F\u002Fstatic.pepy.tech\u002Fbadge\u002Fadversarial-robustness-toolbox)](https:\u002F\u002Fpepy.tech\u002Fproject\u002Fadversarial-robustness-toolbox)\n[![Downloads](https:\u002F\u002Fstatic.pepy.tech\u002Fbadge\u002Fadversarial-robustness-toolbox\u002Fmonth)](https:\u002F\u002Fpepy.tech\u002Fproject\u002Fadversarial-robustness-toolbox)\n[![CII Best Practices](https:\u002F\u002Fbestpractices.coreinfrastructure.org\u002Fprojects\u002F5090\u002Fbadge)](https:\u002F\u002Fbestpractices.coreinfrastructure.org\u002Fprojects\u002F5090)\n\n[中文README请按此处](README-cn.md)\n\n \u003Cdiv align=\"center\">\n  \u003Cpicture>\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"docs\u002Fimages\u002Flfaidata-project-badge-graduate-color_dark.png\" width=\"400\" title=\"LF AI & Data\">\n    \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"docs\u002Fimages\u002Flfaidata-project-badge-graduate-color.png\" width=\"400\" title=\"LF AI & Data\">\n    \u003Cimg alt=\"Fallback image description\" src=\"default-image.png\" width=\"400\">\n  \u003C\u002Fpicture>\n\u003C\u002Fdiv>\n\u003Cbr \u002F>\n\nAdversarial Robustness Toolbox (ART) is a Python library for Machine Learning Security. ART is hosted by the \n[Linux Foundation AI & Data Foundation](https:\u002F\u002Flfaidata.foundation) (LF AI & Data). ART provides tools that enable\ndevelopers and researchers to defend and evaluate Machine Learning models and applications against the\nadversarial threats of Evasion, Poisoning, Extraction, and Inference. ART supports all popular machine learning frameworks\n(TensorFlow, Keras, PyTorch, scikit-learn, XGBoost, LightGBM, CatBoost, GPy, etc.), all data types\n(images, tables, audio, video, etc.) and machine learning tasks (classification, object detection, speech recognition,\ngeneration, certification, etc.).\n\n## Adversarial Threats\n\n \u003Cdiv align=\"center\">\n  \u003Cpicture>\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"docs\u002Fimages\u002Fadversarial_threats_attacker_dark.png\" width=\"400 title=\"ART Threats\">\n    \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"docs\u002Fimages\u002Fadversarial_threats_attacker.png\" width=\"400 title=\"ART Threats\">\n    \u003Cimg alt=\"Fallback image description\" src=\"default-image.png\" width=\"400\">\n  \u003C\u002Fpicture>\n\u003C\u002Fdiv>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fimages\u002Fadversarial_threats_art.png?raw=true\" width=\"400\" title=\"ART Matrix\">\n\u003C\u002Fp>\n\u003Cbr \u002F>\n\n## ART for Red and Blue Teams (selection)\n\n \u003Cdiv align=\"center\">\n  \u003Cpicture>\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"docs\u002Fimages\u002Fwhite_hat_blue_red_dark.png\" width=\"800 title=\"ART Red and Blue Teams\">\n    \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"docs\u002Fimages\u002Fwhite_hat_blue_red.png\" width=\"800 title=\"ART Red and Blue Teams\">\n    \u003Cimg alt=\"Fallback image description\" src=\"default-image.png\" width=\"800\">\n  \u003C\u002Fpicture>\n\u003C\u002Fdiv>\n\u003Cbr \u002F>\n\n## Learn more\n\n| **[Get Started][get-started]**     | **[Documentation][documentation]**     | **[Contributing][contributing]**           |\n|-------------------------------------|-------------------------------|-----------------------------------|\n| - [Installation][installation]\u003Cbr>- [Examples](examples\u002FREADME.md)\u003Cbr>- [Notebooks](notebooks\u002FREADME.md) | - [Attacks][attacks]\u003Cbr>- [Defences][defences]\u003Cbr>- [Estimators][estimators]\u003Cbr>- [Metrics][metrics]\u003Cbr>- [Technical Documentation](https:\u002F\u002Fadversarial-robustness-toolbox.readthedocs.io) | - [Slack](https:\u002F\u002Fibm-art.slack.com), [Invitation](https:\u002F\u002Fjoin.slack.com\u002Ft\u002Fibm-art\u002Fshared_invite\u002FenQtMzkyOTkyODE4NzM4LTA4NGQ1OTMxMzFmY2Q1MzE1NWI2MmEzN2FjNGNjOGVlODVkZDE0MjA1NTA4OGVkMjVkNmQ4MTY1NmMyOGM5YTg)\u003Cbr>- [Contributing](CONTRIBUTING.md)\u003Cbr>- [Roadmap][roadmap]\u003Cbr>- [Citing][citing] |\n\n[get-started]: https:\u002F\u002Fgithub.com\u002FTrusted-AI\u002Fadversarial-robustness-toolbox\u002Fwiki\u002FGet-Started\n[attacks]: https:\u002F\u002Fgithub.com\u002FTrusted-AI\u002Fadversarial-robustness-toolbox\u002Fwiki\u002FART-Attacks\n[defences]: https:\u002F\u002Fgithub.com\u002FTrusted-AI\u002Fadversarial-robustness-toolbox\u002Fwiki\u002FART-Defences\n[estimators]: https:\u002F\u002Fgithub.com\u002FTrusted-AI\u002Fadversarial-robustness-toolbox\u002Fwiki\u002FART-Estimators\n[metrics]: https:\u002F\u002Fgithub.com\u002FTrusted-AI\u002Fadversarial-robustness-toolbox\u002Fwiki\u002FART-Metrics\n[contributing]: https:\u002F\u002Fgithub.com\u002FTrusted-AI\u002Fadversarial-robustness-toolbox\u002Fwiki\u002FContributing\n[documentation]: https:\u002F\u002Fgithub.com\u002FTrusted-AI\u002Fadversarial-robustness-toolbox\u002Fwiki\u002FDocumentation\n[installation]: https:\u002F\u002Fgithub.com\u002FTrusted-AI\u002Fadversarial-robustness-toolbox\u002Fwiki\u002FGet-Started#setup\n[roadmap]: https:\u002F\u002Fgithub.com\u002FTrusted-AI\u002Fadversarial-robustness-toolbox\u002Fwiki\u002FRoadmap\n[citing]: https:\u002F\u002Fgithub.com\u002FTrusted-AI\u002Fadversarial-robustness-toolbox\u002Fwiki\u002FContributing#citing-art\n\nThe library is under continuous development. Feedback, bug reports and contributions are very welcome!\n\n# Acknowledgment\nThis material is partially based upon work supported by the Defense Advanced Research Projects Agency (DARPA) under\nContract No. HR001120C0013. Any opinions, findings and conclusions or recommendations expressed in this material are\nthose of the author(s) and do not necessarily reflect the views of the Defense Advanced Research Projects Agency (DARPA).\n","Adversarial Robustness Toolbox (ART) 是一个用于增强机器学习模型安全性的Python库。它提供了多种工具来帮助开发者和研究人员抵御和评估对抗性攻击，包括逃逸、投毒、提取和推理攻击。ART 支持所有主流的机器学习框架（如TensorFlow、Keras、PyTorch等）以及各种数据类型（图像、表格、音频、视频等），适用于分类、对象检测、语音识别等多种任务。该工具箱特别适合在需要确保AI系统安全性和可靠性的场景中使用，例如金融、医疗保健或自动驾驶等领域。",2,"2026-06-11 03:24:40","top_topic"]