I See You! Robust Measurement of Adversarial Behavior

Lars Ankile, Matheus X.V. Ferreira, David Parkes

Keywords: multi-agent security, blockchain, robust measurement, malicious activity

TL;DR: This paper introduces a novel surveillance metric for quantifying manipulative behavior in multi-agent systems, demonstrated through a natural experiment with data from a blockchain-based distributed exchange.

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.

Submission Number: 10