Counterfit

Tool (not an eval — tooling/reference entry)

CLI for security testing classic ML models.

Category: Adversarial ML (classic)
Insurance exposure: Model failure
Publisher: Microsoft
Publisher type: Big tech
License: MIT
Status: Stale (>12mo)
Last commit: 2025-07-18
Stars: 945

View source on GitHub →

Wanich Risk Lab, 2026.