Skip to player
Research
Offensive AI Security
›
Jailbreaks as Optimization
›
Robustness and Its Limits: Adversarial Training, Classifiers, and Why Provable Bounds Stay Small
Contents
Host
Expert
Murali Chillakuru
Press play to begin the walkthrough.
0:00
15:22
1×
1.25×
1.5×
0.85×
CC
Jailbreaks as Optimization · 5 / 5
Robustness and Its Limits: Adversarial Training, Classifiers, and Why Provable Bounds Stay Small
Play
Back