This article presents a comprehensive survey on adversarial attacks on deep learning in Computer Vision. It reviews methods for designing adversarial attacks, analyzes their existence, and proposes defenses against them. The authors acknowledge contributions from various researchers and support from ARC grant DP160101458. Deep learning has become central to artificial intelligence, particularly in Computer Vision applications such as self-driving cars and surveillance. However, recent studies have shown that deep neural networks are vulnerable to adversarial attacks, where subtle perturbations to inputs can lead to incorrect predictions. These attacks pose a serious threat to the practical success of deep learning. The article covers a wide range of adversarial attack techniques, including image classification, real-world scenarios, and defenses. It also discusses the broader research direction and concludes with a discussion on the implications and future directions.This article presents a comprehensive survey on adversarial attacks on deep learning in Computer Vision. It reviews methods for designing adversarial attacks, analyzes their existence, and proposes defenses against them. The authors acknowledge contributions from various researchers and support from ARC grant DP160101458. Deep learning has become central to artificial intelligence, particularly in Computer Vision applications such as self-driving cars and surveillance. However, recent studies have shown that deep neural networks are vulnerable to adversarial attacks, where subtle perturbations to inputs can lead to incorrect predictions. These attacks pose a serious threat to the practical success of deep learning. The article covers a wide range of adversarial attack techniques, including image classification, real-world scenarios, and defenses. It also discusses the broader research direction and concludes with a discussion on the implications and future directions.