A comprehensive survey of adversarial defense techniques in the visual domain

In recent years, deep neural networks (DNNs) have achieved widespread success in computer vision tasks, including face recognition, autonomous driving, and medical diagnosis. However, their vulnerability to adversarial attacks has also raised serious concerns regarding system security and reliability. This paper provides a comprehensive overview of recent advances in adversarial defense methods in computer vision. It explores defense strategies for Large Vision-Language Models (LVLMs) while covering traditional adversarial defense methods. The article first explains the basic concepts of adversarial samples, their generation principles, and their actual threats in white-box, black-box and physical worlds. It then systematically combs through the multi-dimensional defense strategies based on model architecture design, dynamic adversarial training, and input-output space purification. Meanwhile, for the security challenges of LVLM in the era of significant models, two types of strategies, input-output space defense and dynamic training defense, are discussed. Finally, this paper summarizes the key issues facing adversarial defense and provides an outlook on future research directions. • Comprehensive survey on visual adversarial defense. • Explores defenses for Large Vision-Language Models. • Identifies challenges and future research directions. • Summary of defense methods and adversarial robustness across datasets.