4 papers
Repurposing Backdoors for Good: Ephemeral Intrinsic Proofs for Verifiable Aggregation in Cross-silo Federated Learning
Xian Qin, Xue Yang, Xiaohu Tang
While Secure Aggregation (SA) protects update confidentiality in Cross-silo Federated Learning, it fails to guarantee aggregation integrity, allowing malicious servers to silently…
Orthogonal Soft Pruning for Efficient Class Unlearning
Qinghui Gong, Xue Yang, Xiaohu Tang
Efficient and controllable data unlearning in federated learning remains challenging, due to the trade-off between forgetting and retention performance. Especially under non-indepe…
Efficient Byzantine-Robust Privacy-Preserving Federated Learning via Dimension Compression
Xian Qin, Xue Yang, Xiaohu Tang
Federated Learning (FL) allows collaborative model training across distributed clients without sharing raw data, thus preserving privacy. However, the system remains vulnerable to…
Efficiently Achieving Secure Model Training and Secure Aggregation to Ensure Bidirectional Privacy-Preservation in Federated Learning
Xue Yang, Depan Peng, Yan Feng +3
Bidirectional privacy-preservation federated learning is crucial as both local gradients and the global model may leak privacy. However, only a few works attempt to achieve it, and…