no code implementations • 19 Jun 2023 • Yuexin Xuan, Xiaojun Chen, Zhendong Zhao, Bisheng Tang, Ye Dong
The main challenge of this attack is to allow an attacker without access to the data labels, to perform an effective attack.
no code implementations • CVPR 2022 • Zhendong Zhao, Xiaojun Chen, Yuexin Xuan, Ye Dong, Dakui Wang, Kaitai Liang
Backdoor attack is a type of serious security threat to deep learning models. An adversary can provide users with a model trained on poisoned data to manipulate prediction behavior in test stage using a backdoor.