Towards a Novel Perspective on Adversarial Examples Driven by Frequency

arXiv:2404.10202v1 Announce Type: new
Abstract: Enhancing our understanding of adversarial examples is crucial for the secure application of machine learning models in real-world scenarios. A prevalent method for analyzing adversarial examples is through a frequency-based approach. However, existing research indicates that attacks designed to exploit low-frequency or high-frequency information can enhance attack performance, leading to an unclear relationship between adversarial perturbations and different frequency components. In this paper, we seek to demystify this relationship by exploring the characteristics of adversarial …

abstract adversarial adversarial examples application arxiv attacks cs.ai cs.lg examples exploit however information low machine machine learning machine learning models novel perspective research through type understanding world