Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

TLDR

Deep learning powers modern computer‑vision applications, yet recent evidence shows that imperceptible adversarial perturbations can reliably fool these models, posing a serious threat that has spurred extensive research. This paper offers the first comprehensive survey of adversarial attacks on deep‑learning computer‑vision systems. We review attack design, existence analysis, defense proposals, real‑world evaluations, and synthesize future research directions.

Abstract

Deep learning is at the heart of the current rise of artificial intelligence. In the field of computer vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas, deep neural networks have demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in practice. This fact has recently led to a large influx of contributions in this direction. This paper presents the first comprehensive survey on adversarial attacks on deep learning in computer vision. We review the works that design adversarial attacks, analyze the existence of such attacks and propose defenses against them. To emphasize that adversarial attacks are possible in practical conditions, we separately review the contributions that evaluate adversarial attacks in the real-world scenarios. Finally, drawing on the reviewed literature, we provide a broader outlook of this research direction.