Adversarial machine learning for cybersecurity and computer vision: Current developments and challenges. (21st April 2020)

• Record Type: Journal Article
• Authors: Xi, Bowei
• Is Part Of: Wiley interdisciplinary reviews. Volume 12:Number 5(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-04-21
• Subjects: adversarial machine learning -- cybersecurity -- deep learning -- evasion attack -- poisoning attack; Mathematical statistics -- Data processing -- Periodicals; Science -- Data processing -- Periodicals; Social sciences -- Data processing -- Periodicals; Mathematical statistics -- Periodicals; 519.50285
• DOI: 10.1002/wics.1511
• Languages: English
• ISSNs: 1939-5108

Abstract

Abstract: We provide a comprehensive overview of adversarial machine learning focusing on two application domains, that is, cybersecurity and computer vision. Research in adversarial machine learning addresses a significant threat to the wide application of machine learning techniques—they are vulnerable to carefully crafted attacks from malicious adversaries. For example, deep neural networks fail to correctly classify adversarial images, which are generated by adding imperceptible perturbations to clean images. We first discuss three main categories of attacks against machine learning techniques—poisoning attacks, evasion attacks, and privacy attacks. Then the corresponding defense approaches are introduced along with the weakness and limitations of the existing defense approaches. We notice adversarial samples in cybersecurity and computer vision are fundamentally different. While adversarial samples in cybersecurity often have different properties/distributions compared with training data, adversarial images in computer vision are created with minor input perturbations. This further complicates the development of robust learning techniques, because a robust learning technique must withstand different types of attacks. This article is categorized under: Statistical Learning and Exploratory Methods of the Data Sciences > Clustering and Classification Statistical Learning and Exploratory Methods of the Data Sciences > Deep Learning Statistical and Graphical Methods of Data Analysis > Robust Methods Abstract : Poisoning attack contaminates the training data to render a classifier useless; evasion attack generates adversarial samples at test time; membership inference attack and model inversion attack aim to infer information about data points used in the training process.