A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attacks

TL;DR

This survey comprehensively reviews the robustness and safety of 2D and 3D deep learning models against adversarial attacks, highlighting recent progress, challenges, and future directions for trustworthy AI.

Contribution

First systematic investigation of adversarial attacks on 3D models, with a comprehensive overview of over 170 papers on robustness against various attacks.

Findings

Extensive review of 2D and 3D adversarial attacks

Identification of physical adversarial threats impacting safety

Insights into future research challenges and directions

Abstract

Benefiting from the rapid development of deep learning, 2D and 3D computer vision applications are deployed in many safe-critical systems, such as autopilot and identity authentication. However, deep learning models are not trustworthy enough because of their limited robustness against adversarial attacks. The physically realizable adversarial attacks further pose fatal threats to the application and human safety. Lots of papers have emerged to investigate the robustness and safety of deep learning models against adversarial attacks. To lead to trustworthy AI, we first construct a general threat model from different perspectives and then comprehensively review the latest progress of both 2D and 3D adversarial attacks. We extend the concept of adversarial examples beyond imperceptive perturbations and collate over 170 papers to give an overview of deep learning model robustness against various adversarial attacks. To the best of our knowledge, we are the first to systematically investigate adversarial attacks for 3D models, a flourishing field applied to many real-world applications. In addition, we examine physical adversarial attacks that lead to safety violations. Last but not least, we summarize present popular topics, give insights on challenges, and shed light on future research on trustworthy AI.