Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection
cs.CV, cs.CL, cs.CR
Submitted: 2025-07-03
Updated: 2026-11-17
Terminology
Sources
- GPT-4 Technical Report
- Qwen2.5-VL Technical Report
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
- Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
- When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs
- Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey
- ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time
- Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
- Adversarial Robustness for Visual Grounding of Multimodal Large Language Models
- FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts
- VLSBench: Unveiling Visual Leakage in Multimodal Safety
- JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models
- H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking
- SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
- T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation
- GuardReasoner: Towards Reasoning-based LLM Safeguards
- FlipAttack: Jailbreak LLMs via Flipping
- GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
- From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs