Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggers

no code implementations • 10 Jun 2022 • Nan Luo, Yuanzhang Li, Yajie Wang, Shangbo Wu, Yu-an Tan, Quanxin Zhang

Clean-label settings make the attack more stealthy due to the correct image-label pairs, but some problems still exist: first, traditional methods for poisoning training data are ineffective; second, traditional triggers are not stealthy which are still perceptible.

Backdoor Attack backdoor defense +1

Enhanced CNN for image denoising

no code implementations • 28 Oct 2018 • Chunwei Tian, Yong Xu, Lunke Fei, Junqian Wang, Jie Wen, Nan Luo

Owing to flexible architectures of deep convolutional neural networks (CNNs), CNNs are successfully used for image denoising.

Image Denoising