Matteo Meucci’s Post

📢  The OWASP AI Testing Guide v1 is officially released! Today marks a major milestone for the global AI community: the first open, community-driven standard for trustworthiness testing of AI systems is now available. The OWASP AI Testing Guide fills this gap by establishing a practical standard for trustworthiness testing of AI systems, offering a unified, technology-agnostic methodology that evaluates not only security threats but the broader trustworthiness properties required by responsible and regulatory-aligned AI deployments. 👉 Download the PDF https://lnkd.in/dMKCed8N 👉 Browse it on GitHub https://lnkd.in/dS3SUigF A huge thank you to all the authors: Julio AraujoRoei ArpalyIsaac BentleyYoni Birman, PhD • Henriette Cramer • Luca Demetrio • @DotDotSlash • Federico DottaDidier DurandAlmog Langleben • @Grao Melo • Matteo MeucciMarco MoranaMaura Pintor☁ Jeremy Redmond 🔒Federico RicciutiMartí Jordà RocaSita Ram SaiDhanith KrishnaNicolas Humblot Many thanks to the incredible contributors, reviewers, and practitioners who helped shape this release. Together we are building the foundation of Trustworthy AI OWASP® Foundation. #OWASP #AIsecurity #AITesting #LLM #ResponsibleAI #OWASPAITG #TrustworthyAI

  • No alternative text description for this image
  • No alternative text description for this image

Matteo are you still taking in submissions? My team and I got some techniques we’d like to contribute.

Great guide on how to test correctly AI systems, thanks for the work 🙌

Indeed, major milestone led by a great team. Looking forward for future contributions

Matteo Meucci so what is coming out next? CIS hardening guide for AI? Vulnerability Assessment scanner for AI, SAST DAST for AI? i checked Perplexity, so far no such products yet!

Might be of interest / adjacent to your area Rochelle Harris ?

I have tested it in beta, it's a new step with OWASP.

Brilliant..can't wait to check it out.

See more comments

To view or add a comment, sign in

Explore content categories