Skip to player
Research
Offensive AI Security
›
Alignment & Fine-Tuning Attacks
›
Defenses: Safety-Preserving Fine-Tuning, Tamper-Resistance, and Adaptive Evaluation
Contents
Host
Expert
Murali Chillakuru
Press play to begin the walkthrough.
0:00
16:37
1×
1.25×
1.5×
0.85×
CC
Alignment & Fine-Tuning Attacks · 5 / 5
Defenses: Safety-Preserving Fine-Tuning, Tamper-Resistance, and Adaptive Evaluation
Play
Back