Target-free Latent Safety Alignment

arXiv:2610.04467v1 Announce Type: cross Abstract: Large language models (LLMs) remain highly vulnerable to jailbreak attacks that induce harmful behaviors and circumvent safety alignment. To defend against such attacks, adversarial training paradigms have been proposed to first simulate failure modes and then train the model to correct them, yielding promising improvements in safety alignment. However, these methods typically construct adversarial samples either by encouraging fixed harmful target completions or by performing targeted activation ablation derived from fixed benign--harmful data pairs. As a result, the generated adversarial samples tend to induce homogeneous harmful behaviors that poorly reflect the diversity of behaviors elicited by real-world jailbreak attacks. This behavior-level narrowness fundamentally limits their robustness. To address this issue, we propose a target-free adversarial training framework that generates adversarial samples in an unsupervised manner. By amplifying and diversifying behavior-level shifts in the model's latent space, our approach produces semantically diverse adversarial samples that induce a wide range of harmful behaviors. This expanded behavioral coverage exposes more diverse failure modes and thereby improves safety alignment. To quantify this effect, we use semantic entropy as an output-level measure of adversarial behavioral diversity. Empirically, our method elicits diverse harmful behaviors in the target model, substantially mitigating behavioral narrowness and improving robustness to jailbreak attacks.

Abstract:Large language models (LLMs) remain highly vulnerable to jailbreak attacks that induce harmful behaviors and circumvent safety alignment. To defend against such attacks, adversarial training paradigms have been proposed to first simulate failure modes and then train the model to correct them, yielding promising improvements in safety alignment. However, these methods typically construct adversarial samples either by encouraging fixed harmful target completions or by performing targeted activation ablation derived from fixed benign--harmful data pairs. As a result, the generated adversarial samples tend to induce homogeneous harmful behaviors that poorly reflect the diversity of behaviors elicited by real-world jailbreak attacks. This behavior-level narrowness fundamentally limits their robustness. To address this issue, we propose a target-free adversarial training framework that generates adversarial samples in an unsupervised manner. By amplifying and diversifying behavior-level shifts in the model's latent space, our approach produces semantically diverse adversarial samples that induce a wide range of harmful behaviors. This expanded behavioral coverage exposes more diverse failure modes and thereby improves safety alignment. To quantify this effect, we use semantic entropy as an output-level measure of adversarial behavioral diversity. Empirically, our method elicits diverse harmful behaviors in the target model, substantially mitigating behavioral narrowness and improving robustness to jailbreak attacks.

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

arXiv:2610.04467 [cs.LG]

(or arXiv:2610.04467v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2610.04467 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

Target-free Latent Safety Alignment

Related coverage