5 Papers
Tao Wang is an academic researcher from Nanjing University of Aeronautics and Astronautics. The author has contributed to research in topics: Computer science & Statistical model. The author has an hindex of 1, co-authored 2 publications.
Chat about Author
Papers
Pain-FL: Personalized Privacy-Preserving Incentive for Federated Learning
TL;DR: Wang et al. as discussed by the authors proposed a contract-based personalized privacy-preserving incentive for federated learning, named Pain-FL, to provide customized payments for workers with different privacy preferences as compensation for privacy leakage cost.
68
FedInv: Byzantine-Robust Federated Learning by Inversing Local Model Updates
TL;DR: FedInv is proposed, a novel Byzantine-robust FL framework by inversing local model updates that significantly outperforms the existing robust FL schemes in defending against stealthy poisoning attacks under highly non-IID data partitions.
55
•Posted Content
FedCom: A Byzantine-Robust Local Model Aggregation Rule Using Data Commitment for Federated Learning.
TL;DR: FedCom as mentioned in this paper is a Byzantine-robust federated learning framework by incorporating the idea of commitment from cryptography, which could achieve both data poisoning and model poisoning tolerant FL under practical Non-IID data partitions.
4
FedCom: Byzantine-Robust Federated Learning Using Data Commitment
Tao Wang,Liming Fang +1 more
- 28 May 2023
TL;DR: An extensive performance evaluation demonstrates FedCom's superior performance compared to the state-of-the-art Byzantine-robust schemes under various rigorous settings, even the attackers do not honestly follow the protocol of FedCom and fabricate the commitments.
1
FLForest: Byzantine-robust Federated Learning through Isolated Forest
Tao Wang,Bo Zhao,Liming Fang +2 more
- 01 Jan 2023
TL;DR: Zhang et al. as discussed by the authors proposed a Byzantine-robust federated learning (FL) framework based on isolated forest, which is more robust in the face of targeted poisoning attacks with few samples and data distributions that are highly non-independent and identically distributed.
1