Red Teaming AI: 50 Years of Failure, But This Time, For Sure!


Posted on in Presentations

After 50 years of pen testing, it’s still hard to build secure systems. "Penetrate + patch" never worked. Shifting left, including threat modeling, is finally getting making headway. Securing LLMs is both challenging and painful because code and data are intermingled. This session will discuss how to deliver AI that’s secure by design, via threat modeling and achievable strategies.

Access This and Other RSAC Conference Presentations with Your Free RSAC Membership

Your RSAC Membership also includes AI-powered summaries, mind maps, and slides for Conference presentations, Group Discussions with experts, and more.

Watch Now >>
Participants
Tanya Janca

Speaker

Staff DevRel, Semgrep

Adam Shostack

Speaker

President, Shostack + Associates


Share With Your Community