Kui Ren

Practical Federated Unlearning: A Target Client-Driven Approach to Model Forgetting

To remove the contribution of specific data from the global model in federated learning, federated unlearning has recently emerged. Existing approaches face challenges such as reliance on full client participation, the need to store historical model updates, and high communication costs. To overcome these limitations,...

Optimal DNN Partitioning and Deployment for Dependable Inference Workflow on End Devices

CROSS-TEE: A Distributed Trusted Execution Environment Architecture for Cross-Module Automotive Security

The rapid development of intelligent, connected, and electrified automotive technologies has significantly enhanced convenience, driving substantial growth in the intelligent connected vehicle (ICV) market, and accelerating the replacement of traditional fuel-powered vehicles. However, these advancements have introduce...