Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Perspectives on Adversarial Classification

Version 1 : Received: 6 September 2020 / Approved: 8 September 2020 / Online: 8 September 2020 (10:25:28 CEST)

How to cite: Rios Insua, D.; Naveiro, R.; Gallego, V. Perspectives on Adversarial Classification. Preprints 2020, 2020090184 (doi: 10.20944/preprints202009.0184.v1). Rios Insua, D.; Naveiro, R.; Gallego, V. Perspectives on Adversarial Classification. Preprints 2020, 2020090184 (doi: 10.20944/preprints202009.0184.v1).

Abstract

Adversarial Classification (AC) is a major subfield within the increasingly important domain of adversarial machine learning (AML). Most approaches to AC so far have followed a classical game-theoretic framework. This requires unrealistic common knowledge conditions untenable in the security settings typical of the AML realm. After reviewing such approaches, we present alternative perspectives on AC based on Adversarial Risk Analysis.

Subject Areas

Classification; Adversarial Machine Learning; Security; Robustness; Adversarial Risk Analysis

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.