Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Yuanhe, Xie, Fangzhou, Zhou, Zhenhong, Li, Zherui, Chen, Hao, Wang, Kun, Guo, Yufei
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
por: Li, Zherui, et al.
Publicado: (2025)

CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models
por: Zhou, Zhenhong, et al.
Publicado: (2025)

Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue
por: Zhou, Zhenhong, et al.
Publicado: (2024)

LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models
por: Zhang, Wei, et al.
Publicado: (2026)

How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
por: Zhou, Zhenhong, et al.
Publicado: (2024)

Resource Consumption Threats in Large Language Models
por: Zhang, Yuanhe, et al.
Publicado: (2026)

Reinforced Lifelong Editing for Language Models
por: Li, Zherui, et al.
Publicado: (2025)

Resource Consumption Red-Teaming for Large Vision-Language Models
por: Gao, Haoran, et al.
Publicado: (2025)

$PD^3F$: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Models
por: Zhang, Yuanhe, et al.
Publicado: (2025)

LIFEBench: Evaluating Length Instruction Following in Large Language Models
por: Zhang, Wei, et al.
Publicado: (2025)

Multimodal Conditioned Diffusive Time Series Forecasting
por: Su, Chen, et al.
Publicado: (2025)

On the Role of Attention Heads in Large Language Model Safety
por: Zhou, Zhenhong, et al.
Publicado: (2024)

Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models
por: Gao, Lang, et al.
Publicado: (2024)

Differences in Text Generated by Diffusion and Autoregressive Language Models
por: Zhang, Zeyang, et al.
Publicado: (2026)

Energy-Based Diffusion Language Models for Text Generation
por: Xu, Minkai, et al.
Publicado: (2024)

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak
por: Wang, Hao, et al.
Publicado: (2024)

Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems
por: Li, Zherui, et al.
Publicado: (2025)

Contrastive Learning for Knowledge-Based Question Generation in Large Language Models
por: Zhang, Zhenhong, et al.
Publicado: (2024)

LADR: Locality-Aware Dynamic Rescue for Efficient Text-to-Image Generation with Diffusion Large Language Models
por: Wang, Chenglin, et al.
Publicado: (2026)

Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment
por: Wang, Kun, et al.
Publicado: (2026)

Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws
por: Jha, Akshita, et al.
Publicado: (2024)

HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States
por: Jiang, Yilei, et al.
Publicado: (2025)

Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models
por: Chen, Jie, et al.
Publicado: (2024)

HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models
por: Zhao, Guoshenghui, et al.
Publicado: (2026)

Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models
por: Li, Jiahui, et al.
Publicado: (2024)

Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment through Latent Acoustic Pattern Triggers
por: Lin, Liang, et al.
Publicado: (2025)

Reversible Diffusion Decoding for Diffusion Language Models
por: Wang, Xinyun, et al.
Publicado: (2026)

Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support
por: Wu, Xiaojun, et al.
Publicado: (2024)

Explainable Multimodal Aspect-Based Sentiment Analysis with Dependency-guided Large Language Model
por: Wang, Zhongzheng, et al.
Publicado: (2026)

Diversity Helps Jailbreak Large Language Models
por: Zhao, Weiliang, et al.
Publicado: (2024)

Fusing Large Language Models with Temporal Transformers for Time Series Forecasting
por: Su, Chen, et al.
Publicado: (2025)

Compromesso! Italian Many-Shot Jailbreaks Undermine the Safety of Large Language Models
por: Pernisi, Fabio, et al.
Publicado: (2024)

Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
por: Li, Yifan, et al.
Publicado: (2024)

Large Language Diffusion Models
por: Nie, Shen, et al.
Publicado: (2025)

LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems
por: Zhang, Yuanhe, et al.
Publicado: (2025)

Lost in Diffusion: Uncovering Hallucination Patterns and Failure Modes in Diffusion Large Language Models
por: Guo, Zhengnan, et al.
Publicado: (2026)

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
por: Yu, Miao, et al.
Publicado: (2024)

MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents
por: Zhou, Zhenhong, et al.
Publicado: (2026)

SafeInt: Shielding Large Language Models from Jailbreak Attacks via Safety-Aware Representation Intervention
por: Wu, Jiaqi, et al.
Publicado: (2025)

Multilingual Jailbreak Challenges in Large Language Models
por: Deng, Yue, et al.
Publicado: (2023)