Zhipeng Wei

This survey provides a comprehensive, structured review of safety research in Embodied AI, analyzing attacks and defenses across the entire embodied pipeline to guide the development of safe, robust, and reliable real-world agents.

The paper introduces MT-JailBench, a modular framework for evaluating multi-turn jailbreaks, demonstrating that controlling experimental components like prompt generation and resource budgets is crucial for fair comparison and understanding attack success.

The paper proposes DMN, a compositional jailbreak framework that utilizes distributed instructions, multimodal evidence, and a number chain task across multiple images to significantly enhance the attack success rate against multimodal LLMs.

D-Judge introduces a semantics-preserving output rewriting defense that disrupts multi-turn jailbreak attacks by misaligning the feedback signal used by an attacker's judge model.

The paper proposes OneReason, a framework that enhances the reasoning capability of generative recommendation models by focusing on improving item perception and structuring user behavior into coherent latent interests.