让下一篇重要论文，不再错过。

原文摘要

Diffusion large language models (dLLMs) have recently emerged as a strong alternative to autoregressive models, generating responses by iteratively refining masked tokens in parallel rather than decoding sequentially. While enabling more efficient and flexible inference, dLLMs remain vulnerable to jailbreak attacks, including recent attacks that exploit properties unique to dLLMs such as bidirectional conditioning and parallel masked-token refinement. In this work, we show that these same properties also expose a safety-relevant detection surface absent from standard autoregressive decoding: even when a jailbreak is difficult to identify from prompt representations alone, it can still be detected from hidden states over masked response positions before any tokens are generated. By training linear classifiers on prompt and pre-decoding response representations, we empirically show that neither view strictly dominates, with each detecting attacks that the other misses. We introduce $\texttt{ReFuse}$ (Representation Fusion), an inference-time detector that fuses the sigmoid harmfulness scores of the two classifiers. Without modifying model weights or the decoding procedure, $\texttt{ReFuse}$ reduces average ASR across multiple jailbreaks from 63.29% for the undefended model and 11.27% for a prompt-only classifier to 3.31%, while keeping average benign refusal on standard utility benchmarks below 1% on LLaDA-8B. Together, these results establish $\texttt{ReFuse}$ as a lightweight jailbreak detector for dLLMs that improves safety beyond prompt-only detection.