4 accepted papers
Large language models remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Defending against novel jailbreaks represents a critical challenge in AI safety. Adversarial training---designed to make models robust against worst-case perturbations---has been the…
Safety preferences are inherently subjective, yet current LLM safety alignment methods often impose universal standards that fail to account for individual sensitivities. In this work, we propose an efficient, training-free method for personalized safety control via inference-time activation interve…
Safety backdoor attacks in large language models (LLMs) enable harmful behaviors to be stealthily triggered while evading detection during normal interactions. The high dimensionality of the trigger search space and the diverse range of potential malicious behaviors in LLMs make this a critical open…
Backdoor attacks pose a critical concern to the practice of using third-party data for AI development. The data can be poisoned to make a trained model misbehave when a predefined trigger pattern appears, granting the attackers illegal benefits. While most proposed backdoor attacks are dirty-label,…