Kai-Wei Zhang

Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents

I-Bench, a collection of seemingly harmless adversarial tasks targeting confidentiality and integrity attacks across three platforms, and HITLCUA, a comprehensive adversarial testing framework that integrates a real virtual machine operating system environment with isolated Docker-based web platforms, and simulates human participation by allowing CUAs to consult an API-simulated user before proceeding with suspicious operations.