A Multimodal Automatic Redteaming Evaluation Based on Atomic Jailbreak Strategy Decoupling and Combination

Multimodal Large Language Models MLLMs have achieved impressive progress in image-text comprehension and generation, yet they remain susceptible to jailbreak attacks that can trigger harmful outputs and pose serious safety concerns. Existing multimodal jailbreak attacks have shown the feasibility...

Multimodal Safety Is Asymmetric: Cross-Modal Exploits Unlock Black-Box MLLMs Jailbreaks

Multimodal large language models MLLMs have demonstrated significant utility across diverse real-world applications. But MLLMs remain vulnerable to jailbreaks, where adversarial inputs can collapse their safety constraints and trigger unethical responses. In this work, we investigate jailbreaks i...