paper-with-me

Papers

Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation

2025-07-25 · Yuanhe Zhang, Fangzhou Xie, Zhenhong Zhou, Zherui Li, Hao Chen, Kun Wang, Yufei Guo arxiv

Large Language Diffusion Models (LLDMs) exhibit comparable performance to LLMs while offering distinct advantages in inference speed and mathematical reasoning tasks.The precise and rapid generation capabilities of LLDMs amplify concerns of harmful generations, while existing jailbreak methodologies designed for Large Language Models (LLMs) prove limited effectiveness against LLDMs and fail to expose safety vulnerabilities.Successful defense cannot definitively resolve harmful generation concerns, as it remains unclear whether LLDMs possess safety robustness or existing attacks are incompatible with diffusion-based architectures.To address this, we first reveal the vulnerability of LLDMs to jailbreak and demonstrate that attack failure in LLDMs stems from fundamental architectural differences.We present a PArallel Decoding jailbreak (PAD) for diffusion-based language models. PAD introduces Multi-Point Attention Attack, which guides parallel generative processes toward harmful outputs that inspired by affirmative response patterns in LLMs. Experimental evaluations across four LLDMs demonstrate that PAD achieves jailbreak attack success rates by 97%, revealing significant safety vulnerabilities. Furthermore, compared to autoregressive LLMs of the same size, LLDMs increase the harmful generation speed by 2x, significantly highlighting risks of uncontrolled misuse.Through comprehensive analysis, we provide an investigation into LLDM architecture, offering critical insights for the secure deployment of diffusion-based language models.

📄 PDF Abstract BibTeX arXiv:2507.19227

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical ReasoningText Generation

Similar Papers 제목 키워드 기반

Many-Turn Jailbreaking

2025-08-09 · Xianjun Yang, Liqiang Xiao, Shiyang Li, Faisal Ladhak 외 arxiv

Current jailbreaking work on large language models (LLMs) aims to elicit unsafe outputs from given prompts. However, it only focuses on single-turn jailbreaking targeting one specific query. On the contrary, the advanced…

Adaptive Probe-based Steering for Robust LLM Jailbreaking

2026-05-19 · Junxi Chen, Junhao Dong, Xiaohua Xie arxiv

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious …

Model extraction

Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation

2026-04-09 · Wenpeng Xing, Moran Fang, Guangtai Wang, Changting Lin 외 arxiv

While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak attacks that circumvent safety constraints. Existing strategies, ranging from heuristic prompt engineering to c…

Prompt Engineering

Sequential Comics for Jailbreaking Multimodal Large Language Models via Structured Visual Storytelling

2025-10-16 · Deyue Zhang, Dongdong Yang, Junjie Mu, Quancheng Zou 외 arxiv

Multimodal large language models (MLLMs) exhibit remarkable capabilities but remain susceptible to jailbreak attacks exploiting cross-modal vulnerabilities. In this work, we introduce a novel method that leverages sequen…

Visual Storytelling

FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction

2025-09-25 · Runqi Lin, Alasdair Paren, Suqin Yuan, Muyang Li 외 arxiv

The integration of new modalities enhances the capabilities of multimodal large language models (MLLMs) but also introduces additional vulnerabilities. In particular, simple visual jailbreaking attacks can manipulate ope…