 |
Pengfei Xia I am currently working at Huawei, specializing in AI & System. Prior to that, I studied for my Ph.D. degree at the University of Science and Technology of China under the supervision of Prof. Bin Li and Prof. Jingsong He during September 2017 to June 2023. Email: xpengfei (at) mail.ustc.edu.cn [Google Scholar] |
Research Interests
AI & System
AI & Security
Backdoor Attacks
Education
Ph.D. in Department of Electronic Engineering and Information Science, University of Science and Technology of China, September 2017 - June 2023.
B.Sc. in School of Information and Electrical Engineering, China University of Mining and Technology, September 2011 - June 2015.
Publications
A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
Ziqiang Li, Hong Sun, Pengfei Xia, Beihao Xia, Xue Rui, Wei Zhang, Qinglang Guo, Zhangjie Fu, Bin Li
IEEE Transactions on Information Forensics and Security, 2024Frequency Decomposition to Tap the Potential of Single Domain for Generalization
Hongjing Niu, Qingyue Yang, Pengfei Xia, Wei Zhang, Bin Li, Feng Zhao
British Machine Vision Conference (BMVC), 2024Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search
Pengfei Xia, Ziqiang Li, Bin Li
Genetic and Evolutionary Computation Conference (GECCO) Workshops, 2024Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
Ziqiang Li*, Hong Sun*, Pengfei Xia, Heng Li, Beihao Xia, Yi Wu, Bin Li
International Conference on Learning Representations (ICLR), 2024An Empirical Study of Backdoor Attacks on Masked Autoencoders
Shuli Zhuang, Pengfei Xia, Bin Li
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023Exploring the Effect of High-frequency Components in GANs Training
Ziqiang Li, Pengfei Xia, Xue Rui, Bin Li
ACM Transactions on Multimedia Computing, Communications, and Applications, 2022A Systematic Survey of Regularization and Normalization in GANs
Ziqiang Li, Muhammad Usman, Rentuo Tao, Pengfei Xia, Chaoyue Wang, Huanhuan Chen, Bin Li
ACM Computing Surveys, 2022A New Perspective on Stabilizing GANs Training: Direct Adversarial Training
Ziqiang Li, Pengfei Xia, Rentuo Tao, Hongjing Niu, Bin Li
IEEE Transactions on Emerging Topics in Computational Intelligence, 2022Towards Robust Detection and Segmentation Using Vertical and Horizontal Adversarial Training
Yongduo Sui, Tianlong Chen, Pengfei Xia, Shuyao Wang, Bin Li
International Joint Conference on Neural Networks (IJCNN), 2022Data-Efficient Backdoor Attacks
Pengfei Xia, Ziqiang Li, Wei Zhang, Bin Li
International Joint Conference on Artificial Intelligence (IJCAI), 2022 [Long Oral]Enhancing Backdoor Attacks with Multi-Level MMD Regularization
Pengfei Xia, Hongjing Niu, Ziqiang Li, Bin Li
IEEE Transactions on Dependable and Secure Computing, 2022On the Receptive Field Misalignment in CAM-based Visual Explanations
Pengfei Xia, Hongjing Niu, Ziqiang Li, Bin Li
Pattern Recognition Letters, 2021Improving Resistance to Adversarial Deformations by Regularizing Gradients
Pengfei Xia, Bin Li
Neurocomputing, 2021Understanding the Error in Evaluating Adversarial Robustness
Pengfei Xia, Ziqiang Li, Hongjing Niu, Bin Li
arXiv preprint arXiv:2101.02325, 2021Image Caption Generation with Feature Fusion Module
Pengfei Xia, Jingsong He, Jin Yin
Multimedia Tools and Applications, 2020Online Hard Region Mining for Semantic Segmentation
Jin Yin*, Pengfei Xia*, Jingsong He
Neural Processing Letters, 2019
(* indicates equal contribution)