2025

Stealthy Patch-Wise Backdoor Attack in 3D Point Cloud via Curvature Awareness

Yu Feng, Dingxin Zhang, Dongnan Liu, Runkai Zhao, Yong Xia, Heng Huang, Weidong Cai

Arxiv 2025

We propose SPBA, a stealthy patch-wise backdoor attack for 3D point clouds that leverages local spectral perturbations guided by geometric complexity to achieve high attack success rates while maintaining state-of-the-art imperceptibility.

Stealthy Patch-Wise Backdoor Attack in 3D Point Cloud via Curvature Awareness

Yu Feng, Dingxin Zhang, Dongnan Liu, Runkai Zhao, Yong Xia, Heng Huang, Weidong Cai

Arxiv 2025

We propose SPBA, a stealthy patch-wise backdoor attack for 3D point clouds that leverages local spectral perturbations guided by geometric complexity to achieve high attack success rates while maintaining state-of-the-art imperceptibility.

Contrastive Neuron Pruning for Backdoor Defense

Yu Feng*, Benteng Ma*, Dongnan Liu, Yanning Zhang, Weidong Cai, Yong Xia (* equal contribution)

IEEE Transactions on Image Processing (TIP) 2025

We propose Contrastive Neuron Pruning (CNP), a label-free defense that leverages contrastive learning to identify and prune backdoor-associated neurons, effectively mitigating backdoor attacks with minimal impact on model structure.

Contrastive Neuron Pruning for Backdoor Defense

Yu Feng*, Benteng Ma*, Dongnan Liu, Yanning Zhang, Weidong Cai, Yong Xia (* equal contribution)

IEEE Transactions on Image Processing (TIP) 2025

We propose Contrastive Neuron Pruning (CNP), a label-free defense that leverages contrastive learning to identify and prune backdoor-associated neurons, effectively mitigating backdoor attacks with minimal impact on model structure.

2023

Federated adaptive reweighting for medical image classification

Benteng Ma*, Yu Feng*, Geng Chen, Changyang Li, Yong Xia (* equal contribution)

Pattern Recognition (PR) 2023

We propose a novel Federated Adaptive Reweighting (FedAR) algorithm for medical image classification. FedAR employs a flexible re-weighting scheme that can balance adaptively the contributions of the amount of data and the performance of the local model on each client to the weight of that client.

Federated adaptive reweighting for medical image classification

Benteng Ma*, Yu Feng*, Geng Chen, Changyang Li, Yong Xia (* equal contribution)

Pattern Recognition (PR) 2023

We propose a novel Federated Adaptive Reweighting (FedAR) algorithm for medical image classification. FedAR employs a flexible re-weighting scheme that can balance adaptively the contributions of the amount of data and the performance of the local model on each client to the weight of that client.

2022

Fiba: Frequency-injection based backdoor attack in medical image analysis

Yu Feng*, Benteng Ma*, Jing Zhang, Shanshan Zhao, Yong Xia, Dacheng Tao (* equal contribution)

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022

We propose a novel Frequency-Injection based Backdoor Attack method (FIBA) that is capable of delivering attacks in various medical image analysis tasks.

Fiba: Frequency-injection based backdoor attack in medical image analysis

Yu Feng*, Benteng Ma*, Jing Zhang, Shanshan Zhao, Yong Xia, Dacheng Tao (* equal contribution)

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022

We propose a novel Frequency-Injection based Backdoor Attack method (FIBA) that is capable of delivering attacks in various medical image analysis tasks.