Giving AI Agents the Keys? USC Engineers Develop Tools to Audit and Monitor AI Agents

AI Agent Working Hard (Credit: MidJourney)

Today’s artificial intelligence (AI) agents can help move files on your desktop, access computer passwords and even make decisions on their own, like a personal assistant. But with great power comes great responsibility — when AI makes a mistake, the results can be catastrophic.

AI agents have already had failures that made headlines. An agent with access to a user’s personal data ended up learning about their workplace frustrations and submitted a resignation letter without asking. Other agents with access to a user’s computer folders were reported to have misinterpreted the command and ended up deleting files and wiping their data entirely.

A team of USC computer scientists led by Yue Zhao is on a mission to develop a safety net to keep AI’s actions accountable, ensuring that humans remain in the loop for key decisions and helping prevent serious consequences.

The team follows a three-phase framework: check an agent before it runs, monitor it while it runs, and reconstruct already completed actions when something goes wrong.

Zhao is an assistant professor at USC Viterbi School of Engineering and the USC Mark and Mary Stevens School of Computing and AI‘s Thomas Lord Department of Computer Science. He also leads the FORTIS Lab, which focuses on auditing and controlling AI risk.