How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses
It addresses security concerns in AI systems for researchers and practitioners, but is incremental as it synthesizes existing work.
This survey compiles recent adversarial attacks and defenses for deep neural networks, highlighting vulnerabilities in critical applications like self-driving vehicles and healthcare, and compares state-of-the-art results under different attacks.
Deep Learning is currently used to perform multiple tasks, such as object recognition, face recognition, and natural language processing. However, Deep Neural Networks (DNNs) are vulnerable to perturbations that alter the network prediction (adversarial examples), raising concerns regarding its usage in critical areas, such as self-driving vehicles, malware detection, and healthcare. This paper compiles the most recent adversarial attacks, grouped by the attacker capacity, and modern defenses clustered by protection strategies. We also present the new advances regarding Vision Transformers, summarize the datasets and metrics used in the context of adversarial settings, and compare the state-of-the-art results under different attacks, finishing with the identification of open issues.