Copertina

Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Miao, Ziqi, Ding, Yi, Li, Lijun, Shao, Jing
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Computation and Language Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities
di: Xiong, Yuan, et al.
Pubblicazione: (2025)

Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
di: Ding, Yi, et al.
Pubblicazione: (2025)

Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios
di: Qu, Jingen, et al.
Pubblicazione: (2025)

IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding
di: Li, Junxian, et al.
Pubblicazione: (2025)

Jailbreaking Attack against Multimodal Large Language Model
di: Niu, Zhenxing, et al.
Pubblicazione: (2024)

Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step
di: Wang, Wenxuan, et al.
Pubblicazione: (2024)

MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs
di: Liu, Yilian, et al.
Pubblicazione: (2026)

Metaphor-based Jailbreak Attacks on Text-to-Image Models
di: Zhang, Chenyu, et al.
Pubblicazione: (2025)

HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models
di: Gao, Sensen, et al.
Pubblicazione: (2024)

Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection
di: Yang, Wenkui, et al.
Pubblicazione: (2026)

Image-Based Geolocation Using Large Vision-Language Models
di: Liu, Yi, et al.
Pubblicazione: (2024)

BSPA: Exploring Black-box Stealthy Prompt Attacks against Image Generators
di: Tian, Yu, et al.
Pubblicazione: (2024)

VLSBench: Unveiling Visual Leakage in Multimodal Safety
di: Hu, Xuhao, et al.
Pubblicazione: (2024)

X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability
di: Lu, Xiaoya, et al.
Pubblicazione: (2025)

JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models
di: Jin, Haibo, et al.
Pubblicazione: (2024)

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
di: Jiang, Zhengyuan, et al.
Pubblicazione: (2025)

When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems
di: Zhao, Shiqian, et al.
Pubblicazione: (2025)

The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense
di: Guo, Yangyang, et al.
Pubblicazione: (2024)

Environmental Injection Attacks against GUI Agents in Realistic Dynamic Environments
di: Zhang, Yitong, et al.
Pubblicazione: (2025)

Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory
di: Zhang, Ce, et al.
Pubblicazione: (2026)

Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks
di: Ying, Zonghao, et al.
Pubblicazione: (2024)

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

Optical Lens Attack on Monocular Depth Estimation for Autonomous Driving
di: Zhou, Ce, et al.
Pubblicazione: (2024)

Reason2Attack: Jailbreaking Text-to-Image Models via LLM Reasoning
di: Zhang, Chenyu, et al.
Pubblicazione: (2025)

A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation
di: Yang, Hao, et al.
Pubblicazione: (2026)

DeepSight: An All-in-One LM Safety Toolkit
di: Zhang, Bo, et al.
Pubblicazione: (2026)

Understanding Impacts of Electromagnetic Signal Injection Attacks on Object Detection
di: Zhang, Youqian, et al.
Pubblicazione: (2024)

OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation
di: Jia, Xiaojun, et al.
Pubblicazione: (2025)

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

ConSeg: Contextual Backdoor Attack Against Semantic Segmentation
di: Abbasi, Bilal Hussain, et al.
Pubblicazione: (2025)

Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting
di: Chin, Zhi-Yi, et al.
Pubblicazione: (2024)

Image-to-Text Logic Jailbreak: Your Imagination can Help You Do Anything
di: Zou, Xiaotian, et al.
Pubblicazione: (2024)

Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attacks
di: Diao, Yunfeng, et al.
Pubblicazione: (2024)

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models
di: Liao, Qilin, et al.
Pubblicazione: (2025)

Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Models
di: Liu, Jiangtao, et al.
Pubblicazione: (2025)

When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
di: Tian, Yuan, et al.
Pubblicazione: (2026)

Modeling Electromagnetic Signal Injection Attacks on Camera-based Smart Systems: Applications and Mitigation
di: Zhang, Youqian, et al.
Pubblicazione: (2024)

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
di: Jin, Haibo, et al.
Pubblicazione: (2024)

Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach
di: Huang, Linhao, et al.
Pubblicazione: (2025)

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
di: Gu, Xiangming, et al.
Pubblicazione: (2024)