Jan Wehner
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Honeypots for AI Agent Insider Threats
According to the abstract, Jan Wehner and Jam Kraprayoon propose planting decoy opportunities for harmful actions throughout production environments to catch misbehaving AI agents inside organizations. They argue this could detect, incriminate and deter malicious agents, discuss limits, and outline research questions.