Adversarial Robustness Toolbox

Open source

Open source library for evaluating and defending machine learning models against adversarial attacks.

by The Linux FoundationOfficial site ↗Source code ↗

Pricing: free
License: open-source
Open source: Yes

Editorial review

Adversarial Robustness Toolbox has not yet been editorially reviewed. User reviews and published field data below are unaffected — we say so rather than implying an editorial verdict.

Facts & attributes

Every value carries its evidence state. “—” means unknown — never a silent default (P-02).

Identity · Taxonomy

Documentation(HTTPS URL): https://adversarial-robustness-toolbox.readthedocs.io/en/latest/Verified
Tags(open-source;cloud-native): machine learning security, adversarial attacks, red team, blue team, Python libraryVerification pending

Platform · Deployment

Delivery model(SaaS;self-hosted;desktop;mobile;embedded;managed-cloud;appliance): self-hostedVerification pending

Pricing · Licensing

License model(proprietary;open-source;source-available;dual-license): open-sourceVerification pending
Pricing model(free;subscription;usage;seat;asset;transaction;revenue-share;perpetual;custom): freeVerification pending
Source repository(HTTPS URL): https://github.com/Trusted-AI/adversarial-robustness-toolboxVerified
SPDX license IDs(Apache-2.0;MIT): MITVerified

Features · Product · Fit

Core capabilities(authoring;automation;analytics): Tools for evasion, poisoning, extraction, and inference threats, Defences for machine learning models and applications, Support for TensorFlow, Keras, PyTorch, scikit-learn, XGBoost, LightGBM, CatBoost, Handles images, tables, audio, and video data types, Classification, object detection, speech recognition, generation, and certification tasksVerification pending

Audience · Use · Case

Best for(Neutral editorial summary): ML developers and red/blue teams defending and evaluating models against evasion, poisoning, extraction, and inference attacks.Verification pending
Company-size fit(individual;SMB;mid-market;enterprise): individual, SMB, mid-market, enterpriseVerification pending
Primary use cases(build;monitor;automate): Machine learning security, Red team evaluation of ML models, Blue team defences, Adversarial ML researchVerification pending
Skill level(beginner;intermediate;advanced;specialist): specialistVerification pending

Lifecycle · Versioning

Current version(1.12.3): 1.20Verified
Maintenance status(active;maintenance;deprecated;EOL;archived): activeVerification pending

Vendor · Maintainer

Vendor type(commercial;foundation;community;government;consortium;individual): foundationVerified

User reviews

Review policy

No published reviews yet.