Cover Image

Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xiong, Yuan, Miao, Ziqi, Li, Lijun, Qian, Chen, Li, Jie, Shao, Jing
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection
by: Miao, Ziqi, et al.
Published: (2025)

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

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

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

GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents
by: Li, Xueyi, et al.
Published: (2026)

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

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

Exposing Citation Vulnerabilities in Generative Engines
by: Mochizuki, Riku, et al.
Published: (2025)

What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs
by: Kim, Sangyeop, et al.
Published: (2025)

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
by: Struppek, Lukas, et al.
Published: (2026)

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation
by: Li, Lijun, et al.
Published: (2025)

A First Look at GPT Apps: Landscape and Vulnerability
by: Zhang, Zejun, et al.
Published: (2024)

PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety
by: Zhang, Zaibin, et al.
Published: (2024)

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

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

Membership Inference Attacks Against In-Context Learning
by: Wen, Rui, et al.
Published: (2024)

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

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
by: Wang, Jiongxiao, et al.
Published: (2024)

Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
by: Zhang, Xiaozhe, et al.
Published: (2026)

Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety
by: Zhang, Yuyou, et al.
Published: (2025)

MPMA: Preference Manipulation Attack Against Model Context Protocol
by: Wang, Zihan, et al.
Published: (2025)

Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling
by: Li, Zida, et al.
Published: (2026)

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

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
by: Shen, Guobin, et al.
Published: (2025)

Test-Time Backdoor Attacks on Multimodal Large Language Models
by: Lu, Dong, et al.
Published: (2024)

Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation
by: Guo, Wenkai, et al.
Published: (2025)

Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images
by: Naseh, Ali, et al.
Published: (2024)

How Vulnerable Are Edge LLMs?
by: Ding, Ao, et al.
Published: (2026)

ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations
by: Gomaa, Amr, et al.
Published: (2025)

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

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
by: Jiang, Peihai, et al.
Published: (2025)

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

Overlooked Safety Vulnerability in LLMs: Malicious Intelligent Optimization Algorithm Request and its Jailbreak
by: Gu, Haoran, et al.
Published: (2026)

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
by: Xu, Chejian, et al.
Published: (2025)

SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
by: Huang, Caishuang, et al.
Published: (2024)

Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis
by: Zhang, Haoyu, et al.
Published: (2026)

Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
by: Nawal, Aditya, et al.
Published: (2026)

LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops
by: Fu, Jiyuan, et al.
Published: (2025)

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
by: Chen, Yunhao, et al.
Published: (2025)

CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training
by: Li, Qi, et al.
Published: (2026)