Lessons from AI Red Teaming – And How to Apply Them Proactively


Posted on in Presentations

This talk will present the lessons learned from 2 years of AI red teaming at Google and will evaluate realistic attacker scenarios and tactics, techniques, and procedures (TTPs) that affect real-world AI-powered applications and products. Leveraging these lessons for threat modeling helps to ensure the right safeguards are built into AI products from the get-go.

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
Daniel Fabian

Speaker

Principal Digital Arsonist, Google


Share With Your Community