期刊论文

Guo, KH

英文

Expert Systems with Applications

0957-4174

2025

269

126355

10.1016/j.eswa.2024.126355

This work was supported by the National Natural Science Foundation of China under Grants U24A20333 , 62472443 ; National Key R&D Program of China 2023ZD0508201 ; Hunan Provincial Natural Science Foundation, China 2024JJ3032 ; Frontier Cross Project of Central South University, China ( 2023QYJC008 ); The International Science and Technology Innovation Joint Base of Machine Vision and Medical Image Processing in Hunan Province, China ( 2021CB1013 ).

本校为第一机构

With the emergence of advanced backdoor defense methods, the success rate of backdoor attacks in Deep Neural Networks (DNNs) has dramatically decreased. This situation may lead to overconfidence in existing backdoor defense methods. In view of this, we propose an adversarial distillation strategy combined with a Gaussian reinforcement mechanism (ADGR) for enhancing the resilience of backdoor attacks in the face of defenses. This strategy utilizes a backdoor reinforcement based on Gaussian blur to enhance the ability to counter the backdoor defe...