The safeguards map / 2.1 Tester-run
Adversarial Robustness Toolbox (ART)
Drafted with AI
Drafted with AI from the cited sources under the direction of UnGovr staff. UnGovr holds editorial responsibility for this page. How this site is made
A Python library that attacks and defends machine learning models, covering evasion, poisoning, extraction and inference threats.
Where it sits
2.1 Tester-run (primary): Runs adversarial attacks of the evasion, poisoning, extraction and inference kinds against a machine learning model so a developer or researcher can evaluate its robustness.
ART provides tools that enable developers and researchers to defend and evaluate Machine Learning models and applications against the adversarial threats of Evasion, Poisoning, Extraction, and Inference.
captured
Facts
- Concern
- security
- Names the law
- no
- Subject
- AI model
- Used by
- those who make it
- Runs
- by hand
- Tests
- model behavior
Handoffs
None recorded. A mapped entry with no handoff is here for its foundation home.
Collector's note
Placed in 2.1 because the library is driven by a person in code. Its README also pairs the attacks with defenses; only the testing function is mapped.
Every quote is verbatim from a stored capture of the page linked under it. Placement is our reading of the product's own documentation; no publisher has reviewed or endorsed it. Rows CC BY 4.0. Names, marks and logos belong to their owners; logos identify each product and are not part of the dataset.