Trial LLM red-teaming Dual-use
Adversarial Robustness Toolbox
Adversarial Robustness Toolbox (ART) is a Python library from the Linux Foundation AI & Data project for evaluating and defending ML models against evasion, poisoning, extraction, and inference attacks. It supports major ML frameworks and data types, and is used by red and blue teams.
Worth piloting on a real project; expect some rough edges.
Facts
- Repository
- Trusted-AI/adversarial-robustness-toolbox
- Homepage
- github.com
- Listed via
- Curated
- First seen
- 2026-11-08
- License
- MIT
- Stars
- 6,326
- Last commit
- 2026-11-13
- Latest release
- 1.20.1 · 2025-07-07
- Checked
- 2026-11-22
Techniques
Listing is not endorsement. Summaries and notes are AI-assisted and reviewed; repository facts refresh automatically.