Skip to content

Framework

ML Red-Team Playbook — v1.0

Operational guide for adversarial testing of ML systems. Covers test design, evidence collection, and reporting aligned to OWASP LLM Top 10.

frameworksecurityred-team

5 December 2025 · Reseni Security Team

The playbook gives security teams a repeatable process for adversarial testing of ML systems: scoping, threat modelling, evidence collection, reproducibility, and reporting.

It maps test cases to the OWASP LLM Top 10 and the NIST AI RMF GenAI Profile, and includes a redacted sample report you can hand to engineering and leadership stakeholders.

ML Red-Team Playbook — v1.0 · Reseni Labs