Selected

We uncover the security risk of data-free distillation from a poisoned teacher and propose the first countermeasure.

Continual Test-time Adaptation (CTA) is a promising art to secure accuracy gains in continually-changing environments. The state-of-the-art adaptations improve out-of-distribution model accuracy via computation-efficient online test-time gradient …

Federated learning (FL) emerges as a popular distributed learning schema that learns a model from a set of participating users without requiring raw data to be shared. One major challenge of FL comes from heterogeneity in users, which may have …

Instead of isolated properties, we target on a holistic trustworthiness covering every properties in one solution.

We propose a new privacy-preserving learning framework, outsourcing training to cloud without uploading data, which provides more data without injecting noise into gradient or samples.

Protecting privacy in learning while maintaining the model performance has become increasingly critical in many applications that involve sensitive data. Private Gradient Descent (PGD) is a commonly used private learning framework, which noises …

Efficient and federated learning for heterogeneous clients with different memory sizes

A distributed domain/group debiasing framework for unsupervised domain adaptation or fairness enhancement.

Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data. User heterogeneity has imposed significant challenges to FL, which …

On the need of data privacy and more data, we strive to join the knowledge from a fair amount of users to train powerful deep neural networks without sharing data.