Skip to player
Home
Offensive AI Security
›
Jailbreaks as Optimization
›
Robustness and Its Limits: Adversarial Training, Classifiers, and Why Provable Bounds Stay Small
Contents
CC
Host
Expert
Murali Chillakuru
Press play to begin the conversation.
0:00
12:28
1×
1.25×
1.5×
0.85×
Jailbreaks as Optimization · 5 / 5
Robustness and Its Limits: Adversarial Training, Classifiers, and Why Provable Bounds Stay Small
Play
Back to browse
'%3E%3Crect x='26' y='6' width='8' height='34' rx='2' fill='%23e9e4d6' stroke='%23cfc7b4'/%3E%3Cpath d='M26 40 L30 52 L34 40 Z' fill='%23f7f4ea'/%3E%3Crect x='26' y='6' width='8' height='7' rx='2' fill='%238fd8c4'/%3E%3C/g%3E%3C/svg%3E)