English

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection

Cryptography and Security 2026-05-27 v2 Artificial Intelligence Computation and Language Machine Learning

Abstract

Representation Engineering analyses often characterize refusal using static directions extracted from terminal or pooled representations. We ask whether this view misses how refusal is constructed across layer-token positions. Using causal tracing, we identify a \textit{Refusal Trajectory}: a sparse upstream activation pattern that often persists even when attacks such as GCG suppress terminal refusal signals. Based on this observation, we propose SALO (Sparse Activation Localization Operator), a lightweight white-box detector that operates on raw hidden-state volumes from a selected layer window. Across Qwen, Llama, and Mistral models, SALO improves jailbreak detection on several attack families under a fixed XSTest-calibrated operating point. We further analyze static RepE-style baselines, ROI sensitivity, adaptive GCG attacks, and encoded-input boundary cases, clarifying both the promise and limitations of refusal-trajectory monitoring.

Keywords

Cite

@article{arxiv.2605.02958,
  title  = {Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection},
  author = {Xulin Hu and Che Wang and Wei Yang Bryan Lim and Jianbo Gao and Zhong Chen},
  journal= {arXiv preprint arXiv:2605.02958},
  year   = {2026}
}

Comments

Accepted to the 43rd International Conference on Machine Learning (ICML 2026). Camera-ready version