arXiv:2609.36956v1 Announce Type: cross
Abstract: Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely...
By Jesson Wang, Shawn Li, Wei Yang, Franck Dernoncourt, Ryan A. Rossi, Charith Peris, Yue Zhao
The paper proposes a framework that explains why jailbreak attacks succeed against diffusion-based large language models (dLLMs) by viewing safety alignment as shaping a denoising energy landscape. It identifies two attack strategies—obscuring the query’s safety disposition at initialization or forcing the denoising path across an energy barrier mid‑trajectory—and introduces three training‑free detection signals that monitor initial safety disposition and kinetic energy in complementary subspaces. Experiments on several dense and sparse dLLMs show that these signals complement each other, and any attack that evades detection also fails to produce harmful content.
By Thong Bach, Dung Nguyen, Thao Minh Le, Truyen Tran
arXiv:2606. 04027v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autoregressive LLMs.
By Yingzi Ma, Zhengyue Zhao, Xiaogeng Liu, Minhui Xue, Yue Zhao, Chaowei Xiao
arXiv:2606. 25182v1 Announce Type: cross Abstract: Jailbreak attacks reveal a persistent weakness in aligned Large Language Models: carefully crafted prompts can elicit policy-violating responses despite safety training.
By Sofiia Nikolenko, Michele Papucci, Mina Rezaei, Shireen Kudukkil Manchingal
arXiv:2606. 28153v1 Announce Type: cross Abstract: Jailbreak attacks bypass LLM safety alignment, yet their mechanisms remain poorly understood.
By Yanchen Yin, Dongqi Han, Linghui Li
arXiv:2605. 00123v3 Announce Type: replace Abstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts.
By Shubham Kumar, Narendra Ahuja