# embodied-ai
標記為「embodied-ai」的 4 篇文章
Robotics & Embodied AI Security
Security challenges unique to AI systems controlling physical robots and embodied agents: threat landscape, attack surfaces, physical-world constraints, and safety framework vulnerabilities.
roboticsembodied-ai
Frontier Research
Cutting-edge AI security research covering reasoning model attacks, code generation security, computer use agents, AI-powered red teaming, robotics and embodied AI, and alignment faking.
frontierresearchreasoningcode-modelscomputer-usealignment-fakingembodied-ai
機器人與具身 AI 安全
控制實體機器人與具身代理之 AI 系統特有之安全挑戰：威脅景觀、攻擊面、實體世界限制，以及安全框架漏洞。
roboticsembodied-ai
前沿研究
涵蓋推理模型攻擊、程式碼生成安全、電腦使用代理、AI 驅動紅隊演練、機器人與具身 AI，以及對齊造假的尖端 AI 安全研究。
frontierresearchreasoningcode-modelscomputer-usealignment-fakingembodied-ai