Holistic Adversarial Robustness of Deep Learning Models

Abstract

Adversarial robustness studies the worst-case performance of a machine learning model to ensure safety and reliability. With the proliferation of deep-learning-based technology, the potential risks associated with model development and deployment can be amplified and become dreadful vulnerabilities. This paper provides a comprehensive overview of research topics and foundational principles of research methods for adversarial robustness of deep learning models, including attacks, defenses, verification, and novel applications.

survey paper on holistic adversarial robustness for deep learning; published at AAAI 2023 Senior Member Presentation Track