Adversarial Classification

Abstract

In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being  attacked by malicious agents willing to perturb the value of instance covariates in search of certain goals. Such problems pertain to the field of adversarial machine learning and have been mainly dealt with, perhaps implicitly, through game-theoretic ideas with strong underlying common knowledge assumptions. These are not realistic in numerous application domains in relation to security. We present an alternative statistical framework that accounts for the lack of knowledge about the attacker’s behavior using adversarial risk analysis  concepts.

線上視訊請點選連結

附件下載