# safety-reversal
標記為「safety-reversal」的 2 篇文章
Safety Fine-Tuning Reversal Attacks
Techniques for reversing safety fine-tuning through targeted fine-tuning on adversarial datasets.
trainingfine-tuningsafety-reversal
Safety Fine-Tuning Reversal 攻擊s
Techniques for reversing safety fine-tuning through targeted fine-tuning on adversarial datasets.
trainingfine-tuningsafety-reversal