ALA: Naturalness-aware Adversarial Lightness Attack
Published in ACM Multimedia 2023, 2023
The proposed Adversarial Lightness Attack(ALA), a white-box unrestricted adversarial attack that focuses on modifying the lightness of the images, is to enhance the robustness of deep neural networks from a more natural way.
Recommended citation: Yihao Huang, Liangru Sun, Qing Guo, Felix Juefei-Xu, Jiayi Zhu, Jincao Feng, Yang Liu, Geguang Pu. (2023). “ALA: Naturalness-aware Adversarial Lightness Attack.” ACM Multimedia 2023.
Recommended citation: Yihao Huang, Liangru Sun, Qing Guo, Felix Juefei-Xu, Jiayi Zhu, Jincao Feng, Yang Liu, Geguang Pu. (2023). "ALA: Naturalness-aware Adversarial Lightness Attack." ACM Multimedia 2023.