Yihui Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yihui Zhang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Chengyao Xue
School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450002, China
1 shared publication - Guojia Li
School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450002, China
1 shared publication - Mingyue Cao
School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450002, China
1 shared publication - Yan Cao
Zhengzhou University
1 shared publication - Yihong Zhang
School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450002, China
1 shared publication
Latest Publications
- Open Access
- 6 July 2025
- Published by MDPI AG in Electronics
- Vol. 14 (13) , 2724
BASK: Backdoor Attack for Self-Supervised Encoders with Knowledge Distillation Survivability
Backdoor attacks in self-supervised learning pose an increasing threat. Recent studies have shown that knowledge distillation can mitigate these attacks by altering feature representations. In response, we propose BASK, a novel backdoor attack that remains effective after distillation. BASK uses feature weighting and representation alignment strategies to implant persistent backdoors into the encoder’s feature space. This enables transferability to student models. We evaluated BASK on the CIFAR-10 and STL-10 datasets and compared it with existing self-supervised backdoor attacks under four advanced defenses: SEED, MKD, Neural Cleanse, and MiMiC. Our experimental results demonstrate that BASK maintains high attack success rates while preserving downstream task performance. This highlights the robustness of BASK and the limitations of current defense mechanisms.
- 6 July 2025
- Published by MDPI AG in Electronics
- Vol. 14 (13) , 2724
Open AccessBASK: Backdoor Attack for Self-Supervised Encoders with Knowledge Distillation Survivability
Backdoor attacks in self-supervised learning pose an increasing threat. Recent studies have shown that knowledge distillation can mitigate these attacks by altering feature representations. In response, we propose BASK, a novel backdoor attack that remains effective after distillation. BASK uses feature weighting and representation alignment strategies to implant persistent backdoors into the encoder’s feature space. This enables transferability to student models. We evaluated BASK on the CIFAR-10 and STL-10 datasets and compared it with existing self-supervised backdoor attacks under four advanced defenses: SEED, MKD, Neural Cleanse, and MiMiC. Our experimental results demonstrate that BASK maintains high attack success rates while preserving downstream task performance. This highlights the robustness of BASK and the limitations of current defense mechanisms.