arXiv AI June 8, 2026 By Eliron Rahimi, Elad Hirshel, Rom Himelstein, Amit LeVi, Avi Mendelson, Chaim Baskin

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models

arXiv:2602. 02600v3 Announce Type: replace-cross Abstract: Diffusion language models (DLMs) have recently emerged as a competitive alternative to autoregressive (AR) models, offering parallel decoding, competitive generation quality, and initial evidence of improved jailbreak robustness.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 4

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

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

llms diffusion reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 25

What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics

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

llms benchmarks safety

arXiv AI

Jun 29

Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models

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

llms benchmarks safety

arXiv AI

Aug 10

Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models

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

llms benchmarks safety

arXiv Machine Learning

Jun 30

Sparse Autoencoders are Capable LLM Jailbreak Mitigators

arXiv:2602. 12418v2 Announce Type: replace-cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety.

By Yannick Assogba, Jacopo Cortellazzi, Javier Abad, Pau Rodriguez, Xavier Suau, Arno Blaas

llms diffusion safety

arXiv Machine Learning

Jun 2

VERA: Variational Inference Framework for Jailbreaking Large Language Models

arXiv:2506. 22666v3 Announce Type: replace-cross Abstract: The rise of API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods to identify model vulnerabilities in real-world settings.

By Anamika Lochab, Lu Yan, Patrick Pynadath, Xiangyu Zhang, Ruqi Zhang

llms benchmarks safety

Related stories

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

What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics

Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models

Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models

Sparse Autoencoders are Capable LLM Jailbreak Mitigators

VERA: Variational Inference Framework for Jailbreaking Large Language Models