Exploring the Impact of Frequency Components on Adversarial Patch Attacks Against an Image Classifier Model

Résumé fourni par la source

Exceptional advancements in various computer vision tasks, such as identifying and categorizing objects, have been realized through the use of deep learning models, with a particular emphasis on convolutional neural networks (CNNs). Yet, while these models deliver outstanding results, they remain vulnerable to adversarial examples, thereby raising questions about their safety and dependability. In this paper, we investigate the influence of the image characteristics on the efficacy of adversarial patch attack against an image classifier model. We analyzed such characteristics in the frequency domain, where the frequencies indicate the periodicity and information density that contribute to the efficacy of adversarial patches. Our results showed that low-frequency components had significant contribution to the effectiveness of adversarial patch attacks.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.