Adversarial Machine Learning for Cybersecurity and Computer Vision: Current Developments and Challenges

Abstract

We provide a comprehensive overview of adversarial machine learning focusing on two application domains, i.e., 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.

arXiv commentPublished in WIREs Computational Statistics

References in corpus (15)

• Deep Learning with Differential Privacy
• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Poisoning Attacks against Support Vector Machines
• Security Evaluation of Pattern Classifiers under Attack
• Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization
• Black-box Adversarial Attacks with Limited Queries and Information
• Is feature selection secure against training data poisoning?
• Algorithms that Remember: Model Inversion Attacks and Data Protection Law
• On Detecting Adversarial Perturbations
• Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
• Randomized Prediction Games for Adversarial Machine Learning
• Adversarial Learning: A Critical Review and Active Learning Study