Cover Image

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Wenzhuo, Wei, Zhipeng, Ying, Zonghao, Zhang, Deyue, Yang, Dongdong, Zhang, Xiangzheng, Zou, Quanchen
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Probabilistic Modeling of Jailbreak on Multimodal LLMs: From Quantification to Application
by: Xu, Wenzhuo, et al.
Published: (2025)

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

Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models
by: Zou, Quanchen, et al.
Published: (2026)

PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking
by: Zou, Quanchen, et al.
Published: (2025)

Two Frames Matter: A Temporal Attack for Text-to-Video Model Jailbreaking
by: Chen, Moyang, et al.
Published: (2026)

SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
by: Liu, Zhe, et al.
Published: (2026)

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

Robust Privacy: Inference-Time Privacy through Certified Robustness
by: Jin, Jiankai, et al.
Published: (2026)

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
by: Mu, Junjie, et al.
Published: (2025)

Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings
by: Ying, Zonghao, et al.
Published: (2025)

SPARK: Jailbreaking T2V Models by Synergistically Prompting Auditory and Recontextualized Knowledge
by: Ying, Zonghao, et al.
Published: (2025)

MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
by: Zhang, Xinkai, et al.
Published: (2026)

Evolving Deception: When Agents Evolve, Deception Wins
by: Ying, Zonghao, et al.
Published: (2026)

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
by: Ying, Zonghao, et al.
Published: (2026)

Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions
by: Wang, Shenao, et al.
Published: (2026)

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

Enhancing Jailbreak Attacks on LLMs via Persona Prompts
by: Zhang, Zheng, et al.
Published: (2025)

FlipAttack: Jailbreak LLMs via Flipping
by: Liu, Yue, et al.
Published: (2024)

Evolving Security in LLMs: A Study of Jailbreak Attacks and Defenses
by: Shang, Zhengchun, et al.
Published: (2025)

Can LLMs Deeply Detect Complex Malicious Queries? A Framework for Jailbreaking via Obfuscating Intent
by: Shang, Shang, et al.
Published: (2024)

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward
by: Guo, Weiyang, et al.
Published: (2026)

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
by: Wang, Youze, et al.
Published: (2025)

MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation
by: Yan, Lu, et al.
Published: (2025)

DIVER: Dynamic Iterative Visual Evidence Reasoning for Multimodal Fake News Detection
by: Zhou, Weilin, et al.
Published: (2026)

Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles
by: Sun, Xiongtao, et al.
Published: (2024)

Disentangling Fact from Sentiment: A Dynamic Conflict-Consensus Framework for Multimodal Fake News Detection
by: Zhou, Weilin, et al.
Published: (2025)

PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs
by: Wang, Xinkai, et al.
Published: (2025)

Towards Compositional Generalization in LLMs for Smart Contract Security: A Case Study on Reentrancy Vulnerabilities
by: Zhou, Ying, et al.
Published: (2026)

PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs
by: Gong, Xueluan, et al.
Published: (2024)

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring
by: Chu, Junjie, et al.
Published: (2025)

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
by: Chu, Junjie, et al.
Published: (2024)

"To Survive, I Must Defect": Jailbreaking LLMs via the Game-Theory Scenarios
by: Sun, Zhen, et al.
Published: (2025)

Automatic Jailbreaking of the Text-to-Image Generative AI Systems
by: Kim, Minseon, et al.
Published: (2024)

Injecting Universal Jailbreak Backdoors into LLMs in Minutes
by: Chen, Zhuowei, et al.
Published: (2025)

Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks
by: Tong, Haibo, et al.
Published: (2025)

JPRO: Automated Multimodal Jailbreaking via Multi-Agent Collaboration Framework
by: Zhou, Yuxuan, et al.
Published: (2025)

Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy
by: Jeong, Joonhyun, et al.
Published: (2025)

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate
by: Qi, Senmao, et al.
Published: (2025)

Exploiting Prefix-Tree in Structured Output Interfaces for Enhancing Jailbreak Attacking
by: Li, Yanzeng, et al.
Published: (2025)

Analysis of LLMs Against Prompt Injection and Jailbreak Attacks
by: Jaiswal, Piyush, et al.
Published: (2026)