Frontier AI models can now find exploitable vulnerabilities at a pace that changes the economics of attack and defense. This session shares what Tanium's security organization is learning from using them to hunt for vulnerabilities in our own products before anyone else can. We'll cover the approaches we tested, including how we build the harnesses around models and how we triage what they find, along with the challenges we ran into and how we've dealt with them. You'll leave with first-hand results, a practical starting point for applying similar practices to your own software and systems, and a clear picture of what the coming increase in advisories and patches means for your vulnerability management program.

Additional details