扩散语言模型越狱为何成功：能量景观分析

Computer Science > Artificial Intelligence arXiv:2609.30841 (cs) [Submitted on 25 Sep 2026] Title:Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis Authors:Thong Bach, Dung Nguyen, Thao Minh Le, Truyen Tran View a PDF of the paper titled Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis, by Thong Bach and 3 other authors View PDF HTML (experimental) Abstract: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. Comments: Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2609.30841 [cs.AI] (or arXiv:2609.30841v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2609.30841 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Journal reference: NeurIPS 2026 Submission history From: Thong Bach [view email] [v1] Fri, 25 Sep 2026 05:35:36 UTC (441 KB) Full-text links: Access Paper: View a PDF of the paper titled Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis, by Thong Bach and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI new | recent | 2026-09 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators 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. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)