Xiang Zheng
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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.
STARE introduces a novel hierarchical reinforcement learning framework that treats the entire image generation process (denoising trajectory) as an attack surface, significantly improving the detection of multi-modal toxicity vulnerabilities in Vision-Language Models.
Papers
STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack
Xutao Mao, Liangjie Zhao, Tao Liu, Xiang Zheng +2 more
STARE introduces a novel hierarchical reinforcement learning framework that treats the entire image generation process (denoising trajectory) as an attack surface, significantly improving the detectio…