Adversarial learning for coordinate regression through k-layer penetrating representation

• Main Authors: JIANG, Mengxi, SUI, Yulei, LEI, Yunqi., XIE, Xiaofei, LI, Cuihua, LIU, Yang, TSANG, Ivor W.
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2024
• 主題: Artificial neural networks; Backpropagation; Computational modeling; Numerical models; Perturbation methods; Robustness; Task analysis; Information Security
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/8737

Adversarial attack is a crucial step when evaluating the reliability and robustness of deep neural networks (DNNs) models. Most existing attack approaches apply an end-to-end gradient update strategy to generate adversarial examples for a classification or regression problem. However, few of them co...