Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey

TL;DR

This survey reviews adversarial patch attacks and defenses in vision-based deep learning, highlighting recent progress, challenges, and practical implications for enhancing AI security in safety-critical systems.

Contribution

It provides a comprehensive overview of existing adversarial patch attack techniques and defense methods, aiding researchers in understanding current advancements and challenges.

Findings

Summarizes various adversarial patch attack methods.

Discusses detection and defense strategies against patches.

Highlights the importance of robustness in safety-critical AI applications.

Abstract

Adversarial attacks in deep learning models, especially for safety-critical systems, are gaining more and more attention in recent years, due to the lack of trust in the security and robustness of AI models. Yet the more primitive adversarial attacks might be physically infeasible or require some resources that are hard to access like the training data, which motivated the emergence of patch attacks. In this survey, we provide a comprehensive overview to cover existing techniques of adversarial patch attacks, aiming to help interested researchers quickly catch up with the progress in this field. We also discuss existing techniques for developing detection and defences against adversarial patches, aiming to help the community better understand this field and its applications in the real world.