Buchumschlag

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wang, Youze, Hu, Wenbo, Dong, Yinpeng, Liu, Jing, Zhang, Hanwang, Hong, Richang
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Cryptography and Security Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
von: Teng, Ma, et al.
Veröffentlicht: (2024)

SoK: Robustness in Large Language Models against Jailbreak Attacks
von: Xu, Feiyue, et al.
Veröffentlicht: (2026)

Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction
von: Liu, Tong, et al.
Veröffentlicht: (2024)

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models
von: Park, Junyoung, et al.
Veröffentlicht: (2026)

Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models
von: Li, Xiao, et al.
Veröffentlicht: (2024)

Sequential Comics for Jailbreaking Multimodal Large Language Models via Structured Visual Storytelling
von: Zhang, Deyue, et al.
Veröffentlicht: (2025)

CCJA: Context-Coherent Jailbreak Attack for Aligned Large Language Models
von: Zhou, Guanghao, et al.
Veröffentlicht: (2025)

Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks
von: Yan, Yu, et al.
Veröffentlicht: (2026)

AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks
von: Song, Weiming, et al.
Veröffentlicht: (2026)

ShallowJail: Steering Jailbreaks against Large Language Models
von: Liu, Shang, et al.
Veröffentlicht: (2026)

A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
von: Li, Jie, et al.
Veröffentlicht: (2024)

PiCo: Jailbreaking Multimodal Large Language Models via Pictorial Code Contextualization
von: Liu, Aofan, et al.
Veröffentlicht: (2025)

Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
von: Ma, Jiachen, et al.
Veröffentlicht: (2024)

Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space
von: Huang, Yao, et al.
Veröffentlicht: (2025)

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
von: Zhao, Shiji, et al.
Veröffentlicht: (2025)

A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
von: Xu, Zihao, et al.
Veröffentlicht: (2024)

Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language Models
von: Hong, Wenjing, et al.
Veröffentlicht: (2026)

Single-Configuration Attack Success Rate Is Not Enough: Jailbreak Evaluations Should Report Distributional Attack Success
von: Maple, Carsten, et al.
Veröffentlicht: (2026)

Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models
von: Huang, Xijie, et al.
Veröffentlicht: (2024)

Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks via Reinforcement Learning
von: Wang, Zhaoqi, et al.
Veröffentlicht: (2026)

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
von: Ying, Zonghao, et al.
Veröffentlicht: (2025)

Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey
von: Jain, Bhavuk, et al.
Veröffentlicht: (2026)

QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language
von: Zou, Qingsong, et al.
Veröffentlicht: (2025)

Multi-turn Jailbreaking Attack in Multi-Modal Large Language Models
von: Das, Badhan Chandra, et al.
Veröffentlicht: (2026)

ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language Models
von: Cheng, Siyang, et al.
Veröffentlicht: (2025)

Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character
von: Ma, Siyuan, et al.
Veröffentlicht: (2024)

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models
von: Zheng, Baolin, et al.
Veröffentlicht: (2025)

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models
von: Yu, Yongcan, et al.
Veröffentlicht: (2025)

Imperceptible Jailbreaking against Large Language Models
von: Gao, Kuofeng, et al.
Veröffentlicht: (2025)

Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models
von: Tu, Shangqing, et al.
Veröffentlicht: (2024)

Gradient-based Jailbreak Images for Multimodal Fusion Models
von: Rando, Javier, et al.
Veröffentlicht: (2024)

Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models
von: Yang, Fan
Veröffentlicht: (2025)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
von: Jiang, Tanqiu, et al.
Veröffentlicht: (2024)

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
von: Li, Yanjie, et al.
Veröffentlicht: (2025)

FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts
von: Zhang, Ziyi, et al.
Veröffentlicht: (2025)

New Wide-Net-Casting Jailbreak Attacks Risk Large Models
von: Xiang, Qiuchi, et al.
Veröffentlicht: (2026)

AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models
von: Chen, Guangke, et al.
Veröffentlicht: (2025)

Untargeted Jailbreak Attack
von: Huang, Xinzhe, et al.
Veröffentlicht: (2025)

Distract Large Language Models for Automatic Jailbreak Attack
von: Xiao, Zeguan, et al.
Veröffentlicht: (2024)

JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
von: Luo, Weidi, et al.
Veröffentlicht: (2024)