Adversarial Attacks and Defenses in Images, Graphs and Text: A Review
It provides a systematic overview for researchers and practitioners working on security in machine learning, but it is incremental as a review paper.
This paper reviews the state of the art in adversarial attacks and defenses for deep neural networks across images, graphs, and text, addressing concerns about safety-critical applications.
Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised concerns about applying deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types, such as images, graphs and text. Thus, it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures. In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for the three popular data types, i.e., images, graphs and text.