Publications

Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classification proves insufficient when models encounter ethical dilemmas, where the capacity to reason through moral trade-offs creates a distinct attack surface. We formalize this vulnerability through TRIAL, a multi-turn red-teaming methodology that embeds harmful requests within ethical framings. TRIAL achieves high attack success rates across most tested models by systematically exploiting the model's ethical reasoning capabilities to frame harmful actions as morally necessary compromises. Building on these insights, we introduce ERR (Ethical Reasoning Robustness), a defense framework that distinguishes between instrumental responses that enable harmful outcomes and explanatory responses that analyze ethical frameworks without endorsing harmful acts. ERR employs a Layer-Stratified Harm-Gated LoRA architecture, achieving robust defense against reasoning-based attacks while preserving model utility.

Understanding how aligned LLMs internally represent safety is critical for diagnosing alignment vulnerabilities, as it explains why jailbreaks succeed and informs the design of robust alignment strategies. Prior work shows that aligned LLMs encode harmfulness and refusal as separable directions in the residual stream at prompt-side token positions. We show that jailbreaks succeed at prompt encoding by suppressing either the refusal or harmfulness direction before any token is generated, with distinct attack classes occupying separable regions of the harmfulness-refusal plane. Extending the analysis to response-token positions, we find that the model recognizes harmful content while it is generating that content, even when it failed to recognize the input as harmful at the prompt side. Motivated by our findings, we introduce HARC (Harmfulness-And-Refusal Coupling), a fine-tuning method that pairs the two directions across both prompt and response positions. Since the intervention is confined to the harmfulness-refusal subspace, it leaves the rest of the residual stream intact and does not degrade general capability or inflate over-refusal. Across extensive experiments, HARC achieves the strongest robustness-capability-usability trade-off among six baselines spanning the major training-time and inference-time safety methods. The harmfulness and refusal directions at prompt and response positions transfer across the five model families and two scales we tested without architecture-specific tuning.

Aligned Large Language Models (LLMs) have attracted significant attention for their safety, particularly in the context of jailbreak attacks that attempt to bypass guardrails via adversarial prompts. Among existing approaches, the Greedy Coordinate Gradient (GCG) attack pioneered automated jailbreaks through discrete token optimization; however, its low sample efficiency limits practical applicability. In particular, GCG requires approximately 256K evaluations per harmful behavior to achieve a satisfactory jailbreak success rate, due to the inherent difficulty of the underlying discrete optimization problem. In this work, we identify three key factors that limit the sample efficiency of GCG: inaccurate gradient-based estimation, inefficient uniform sampling, and repeated evaluation of previously explored suffixes. To address these issues, we propose Faster-GCG, a streamlined variant of GCG that incorporates distance-based regularization for improved estimation, temperature-controlled sampling for more effective exploration, and a visited-suffix marking mechanism to avoid redundant evaluations. Faster-GCG reduced the required evaluations to 32K, achieving up to an 8× improvement in sampling efficiency and a 7× reduction in wall-clock time compared to GCG. Under this reduced budget, Faster-GCG attained an average jailbreak success rate of 78.1% across five aligned LLMs, and achieved 88.7% against Qwen3.5-4B, outperforming state-of-the-art white-box jailbreak methods.