Adversarial Security Attacks and Perturbations on Machine Learning and Deep Learning Methods

Abstract

The ever-growing big data and emerging artificial intelligence (AI) demand the use of machine learning (ML) and deep learning (DL) methods. Cybersecurity also benefits from ML and DL methods for various types of applications. These methods however are susceptible to security attacks. The adversaries can exploit the training and testing data of the learning models or can explore the workings of those models for launching advanced future attacks. The topic of adversarial security attacks and perturbations within the ML and DL domains is a recent exploration and a great interest is expressed by the security researchers and practitioners. The literature covers different adversarial security attacks and perturbations on ML and DL methods and those have their own presentation styles and merits. A need to review and consolidate knowledge that is comprehending of this increasingly focused and growing topic of research; however, is the current demand of the research communities. In this review paper, we specifically aim to target new researchers in the cybersecurity domain who may seek to acquire some basic knowledge on the machine learning and deep learning models and algorithms, as well as some of the relevant adversarial security attacks and perturbations.

References in corpus (8)

• Explaining and Harnessing Adversarial Examples
• On Evaluating Adversarial Robustness
• Houdini: Fooling Deep Structured Prediction Models
• Adversarial examples for generative models
• A Survey on Resilient Machine Learning
• Designing Adversarially Resilient Classifiers using Resilient Feature Engineering
• AdversariaLib: An Open-source Library for the Security Evaluation of Machine Learning Algorithms Under Attack
• Adequacy of the Gradient-Descent Method for Classifier Evasion Attacks