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Preserved in Portico This version is not peer-reviewed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)
A peer-reviewed article of this Preprint also exists.
Rios Insua, D.; Naveiro, R.; Gallego, V. Perspectives on Adversarial Classification. Mathematics 2020, 8, 1957. Rios Insua, D.; Naveiro, R.; Gallego, V. Perspectives on Adversarial Classification. Mathematics 2020, 8, 1957.
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.
Keywords
Classification; Adversarial Machine Learning; Security; Robustness; Adversarial Risk Analysis
Subject
Computer Science and Mathematics, Probability and Statistics
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment