Oral
in
Workshop: Multi-Agent Security: Security as Key to AI Safety
I See You! Robust Measurement of Adversarial Behavior
Lars Ankile · Matheus Xavier Ferreira · David Parkes
[
Abstract
]
[ Project Page ]
presentation:
Multi-Agent Security: Security as Key to AI Safety
Sat 16 Dec 7 a.m. PST — 3:30 p.m. PST
[
Slides]
Sat 16 Dec 12:10 p.m. PST
— 12:25 p.m. PST
Sat 16 Dec 7 a.m. PST — 3:30 p.m. PST
Abstract:
We introduce the study of non-manipulable measures of manipulative behavior in multi-agent systems. We do this through a case study of decentralized finance (DeFi) and blockchain systems, which are salient as real-world, rapidly emerging multi-agent systems with financial incentives for malicious behavior, for the participation in algorithmic and AI systems, and for the need for new methods with which to measure levels of manipulative behavior. We introduce a new surveillance metric for measuring malicious behavior and demonstrate its effectiveness in a natural experiment to the Uniswap DeFi ecosystem.
Chat is not available.