OWASP Launches AI Testing Guide to Address Security, Bias, and Risk in AI Systems
Security, Friday, June 27th, 2025
The OWASP Foundation has officially introduced the AI Testing Guide (AITG), a new open-source initiative aimed at assisting organizations in the systematic testing and security of artificial intelligence systems.
This guide, led by Matteo Meucci and Marco Morana, serves as a fundamental resource for developers, testers, risk officers, and cybersecurity professionals, promoting best practices in AI system security.
As AI technologies become embedded in critical industries-from finance and healthcare to national security-the need for structured, AI-specific testing has grown significantly. Unlike traditional software, AI systems introduce unique challenges, including non-deterministic behavior, data drift, adversarial attacks, and algorithmic bias. The AITG addresses these issues directly using methodologies derived from OWASP's established practices, including the Web Security Testing Guide (WSTG) and the Mobile Security Testing Guide (MSTG).