Published in KDD, 2025
This paper propose client pricing method for FL data market.
Recommended citation: Zhenyu Wen, Wanglei Feng, Di Wu, Haozhen Hu, Chang Xu, Bin Qian, Zhen Hong, Cong Wang, Shouling Ji. (Accept). "FLMarket: Enabling Privacy-preserved Pre-training Data Pricing for Federated Learning." KDD2025. (CCF A) https://arxiv.org/abs/2411.11713
Published in ICDCS, 2025
This paper propose Edge Model Overlay to address the challenges in SFL.
Recommended citation: Di Wu, Weibo He, Wanglei Feng, Zhenyu Wen, Bin Qian, and Blesson Varghese. (Accept). "EMO: Edge Model Overlays to Scale Model Size in Federated Learning." ICDCS2025. (CCF B) https://arxiv.org/abs/2504.00726
Published in AIOTSYS, 2024
An intelligent scheduling scheme is proposed for the scenario of cloud-side collaborative distillation.
Recommended citation: Gaoyun Lin，Wanglei Feng，Shenlan Luo，Bin Qian. (2024). "Orchestrating Communication and Computation Efficiency in Edge-Based Knowledge Distillation." AIOTSYS.（EI检索） https://ieeexplore.ieee.org/document/10780538
Published in 计算机研究与发展, 2024
文章提出了一种用于检测联邦学习中搭便车客户端的方法，通过比较不同时期梯度更新的相似性来检测攻击者.
Recommended citation: 洪榛，冯王磊，温震宇，吴迪，李涛涛，伍一鸣，王聪，纪守领. (2024). "基于梯度回溯的联邦学习搭便车攻击检测." 计算机研究与发展.（EI检索） https://crad.ict.ac.cn/article/doi/10.7544/issn1000-1239.202330886
Published in IEEE Transactions on Vehicular Technology, 2024
This paper propose a multi-step attack prediction architecture applied in the smart home.
Recommended citation: Taotao Li, Zhen Hong, Wanglei Feng, Li Yu, Zhenyu Wen. (2024). "MS-ZeroWall: Detecting Zero-Day Multi-Step Attack in Smart Home using VAE and HMM." IEEE Transactions on Vehicular Technology. (SCI-2,IF:6.8) https://ieeexplore.ieee.org/document/10507036
Published in IEEE Access, 2024
This paper propose an FL client subset selection algorithm.
Recommended citation: Chang Xu, Hong Liu, Kexin Li, Wanglei Feng, Wei Qi. (2024). "Pretraining Client Selection Algorithm Based on a Data Distribution Evaluation Model in Federated Learning." IEEE Access. (SCI-3,IF:3.9) https://ieeexplore.ieee.org/document/10517589