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...

RedTWIZ: Diverse LLM Red Teaming Via Adaptive Attack Planning

This paper presents the vision, scientific contributions, and technical details of RedTWIZ: an adaptive and diverse multi-turn red teaming framework, to audit the robustness of Large Language Models LLMs in AI-assisted software development. Our work is driven by three major research streams: 1...