cs.CLNov 6, 2026

Beyond the Prompt: Leveraging Pre-Decoding States for Jailbreak Detection in dLLMs

Authors: Adam Hazimeh, Amel Abdelraheem, Ke Wang, Mariam Salman, Ljiljana Dolamic, Gérôme Bovet, Pascal Frossard

Organizations: EPFL, Lausanne, Switzerland · American University of Beirut, Lebanon · Armasuisse, Cyber-Defence Campus, Switzerland

Abstract

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 ReFuse\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, ReFuse\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 ReFuse\texttt{ReFuse} as a lightweight jailbreak detector for dLLMs that improves safety beyond prompt-only detection.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 22, 2026

Harmful Responses Are Jailbreak Templates: Transferring Autoregressive Jailbreaks to Diffusion Language Models

Diffusion large language models (dLLMs) enable flexible masked generation through bidirectional context modeling, but this capability also introduces a distinct jailbreak attack surface. We find that a harmful response to a given query naturally serves as an effective jailbreak template: simply masking a subset of its tokens can induce a dLLM to reconstruct harmful content. Based on this observation, we propose RMT-Jailbreak, a general framework that transfers existing autoregressive (AR) jailbreak attacks to dLLMs through their induced harmful responses. RMT-Jailbreak converts an AR-generated harmful response into a high-mask-ratio template using uniform token retention, and further applies prompt-based safety filtering to mask any remaining visible harmful content. The refined template is then provided to the target dLLM for bidirectional reconstruction. Extensive experiments across multiple AR jailbreak methods and target dLLMs demonstrate the effectiveness and generality of RMT-Jailbreak, revealing strong cross-paradigm transferability of jailbreak attacks.
Sep 25, 2026

Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis

Existing attacks and defenses for diffusion-based large language models (dLLMs) target specific vulnerabilities but lack a shared framework explaining why attacks succeed. We propose one by interpreting safety alignment as shaping the denoising energy landscape: a well-aligned model routes harmful queries toward safe outputs through an energy barrier that separates the two regions. Current jailbreak attacks reduce to two strategies for circumventing this barrier: obscuring the query's safety disposition at initialisation, or intervening mid-trajectory to force the denoising path across the energy barrier. From this perspective and the result that masked diffusion models minimise kinetic energy during denoising, we derive three complementary, training-free detection signals: a step-0 ratio that reads the initial safety disposition from the logit distribution before generation begins, and two trajectory-velocity signals that track kinetic energy in complementary subspaces of the logit space. An attack must either reveal its intent at initialisation or expend kinetic energy to cross the barrier in at least one monitored subspace, so the three signals cover each other's blind spots in the energy budget by construction. Evaluation across three dense dLLMs (LLaDA-8B, LLaDA-1.5, Dream-7B) and a sparse mixture-of-experts dLLM (LLaDA-MoE-7B) confirms this complementarity. In stress tests of known attacks, every configuration that evades detection also fails to produce harmful content, suggesting that the detection and barrier-crossing thresholds are hard to separate.
Jun 1, 2026

MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models

Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autoregressive LLMs. Because mask tokens are native inputs and tokens are committed by confidence rather than position, harmful content can be induced through infilling and outside the monitored prefix. Existing jailbreaks either miss this native infill capability or rely on low-diversity mask-bearing templates applied uniformly across goals, with little structural adaptation or accumulated attack experience. We propose MaskForge, a fully black-box adaptive attack that casts dLLM red-teaming as optimized search over a growing library of structural patterns. MaskForge abstracts successful attempts into reusable schemas, selects goal-compatible patterns with a UCB bandit, and invokes a scorer-guided fallback when the current library fails. Successful attempts are distilled back into the pattern library, enabling experience to accumulate across goals. Across five public dLLMs and three benchmarks, MaskForge achieves an average attack success rate of 79.3%, a 17.6% relative improvement over the strongest competing dLLM baseline. The matured pattern library further transfers to AdvBench without any updates, achieving a 88.2% attack success rate and a 67% relative improvement over the strongest competing baseline.