# computer-use
標記為「computer-use」的 12 篇文章
Computer Use Agent Attacks
Comprehensive analysis of attack vectors targeting AI systems with computer use capabilities, including GUI manipulation, pixel-level injection, and desktop environment exploitation techniques.
Computer Use & GUI Agent Attacks
Security risks of AI agents that interact with graphical interfaces: attack surfaces in browser automation, desktop control, and screen-based reasoning systems.
Screen Capture Injection
Techniques for injecting malicious content through screen capture pipelines used by computer use AI agents, including frame manipulation, capture timing attacks, and pixel-level payload delivery through the visual channel.
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.
Lab: Computer Use Agent Exploitation
Hands-on lab exploring attack vectors against GUI-based computer use agents that interact with screens through vision and action primitives.
Attacks via Screen Capture and Computer-Use AI
Techniques for attacking AI systems that process screen captures, including computer-use agents, screen-reading assistants, and automated UI testing systems.
Computer Use 代理 攻擊s
Comprehensive analysis of attack vectors targeting AI systems with computer use capabilities, including GUI manipulation, pixel-level injection, and desktop environment exploitation techniques.
Computer Use 與 GUI 代理攻擊
與圖形介面互動之 AI 代理的安全風險：瀏覽器自動化、桌面控制，以及以螢幕為基礎之推理系統之攻擊面。
Screen Capture Injection
Techniques for injecting malicious content through screen capture pipelines used by computer use AI agents, including frame manipulation, capture timing attacks, and pixel-level payload delivery through the visual channel.
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。
實作：Computer Use 代理攻擊
探索針對以 GUI 為本之 computer use 代理（透過視覺與動作原語與畫面互動）之攻擊向量的實作課程。
攻擊s via Screen Capture and Computer-Use AI
Techniques for attacking AI systems that process screen captures, including computer-use agents, screen-reading assistants, and automated UI testing systems.