Adversarial Training Can Further Hide a Backdoor, but Does It Improve Trigger Identification?

Summary The Sleeper Agents paper demonstrated that adversarial training on red-team prompts failed to remove a planted backdoor. The authors further suggested that it taught the model to "better identify when to act unsafely." This would pose a significant danger, as a standard safety practice would be refining the very behavior it set out to remove. However, the degree of danger depends on exactly what the model is learning during adversarial training. We discuss how, due to saturation of firing rates, more benign scenarios such as the model's backdoor response being generally weakened are al

• #training
• #backdoor