Identifying Adversary Characteristics from an Observed Attack

ArXi:2603.05625v1 Announce Type: new When used in automated decision-making systems, machine learning (ML) models are vulnerable to data-manipulation attacks. Some defense mechanisms (e.g., adversarial regularization) directly affect the ML models while others (e.g., anomaly detection) act within the broader system. In this paper we consider a different task for defending the adversary, focusing on the attacker, rather than the attack. We present and nstrate a framework for identifying characteristics about the attacker from an observed attack.