Library Header Image Library Header Image

Crashing Browsers—How AI Agents Break the Browser Threat Model


Posted on in Presentations

Browsers, the gateway to the web, have undergone extensive security engineering and threat modeling, making them significantly more difficult to hack. Agentic AI browsers break this model, rendering sound mitigations suddenly ineffective. This talk will show how this enables turning prompt injection into impactful attacks, from stealing local files to fraudulent purchases or full account takeover.

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
Nil Ashkenazi

Speaker

Security Researcher , CyberArk


Share With Your Community