Improving fairness between privileged and less-privileged sensitive attribute groups
(eg,{race, gender}) has attracted lots of attention. To enhance the model performs uniformly …

Collaborative inference (co-inference) accelerates deep neural network inference via
extracting representations at the device and making predictions at the edge server, which …

Federated learning (FL) provides a variety of privacy advantages by allowing clients to
collaboratively train a model without sharing their private data. However, recent studies have …

Machine learning models have shone in a variety of domains and attracted increasing
attention from both the security and the privacy communities. One important yet worrying …

Recent researches demonstrate that deep learning models are vulnerable to membership
inference attacks. Few defenses have been proposed, but suffer from compromising the …

The ever-growing advances of deep learning in many areas including vision,
recommendation systems, natural language processing, etc., have led to the adoption of …

Recent works have shown that Generative Adversarial Networks (GANs) may generalize
poorly and thus are vulnerable to privacy attacks. In this paper, we seek to improve the …

Ensuring a neural network is not relying on protected attributes (eg, race, sex, age) for
predictions is crucial in advancing fair and trustworthy AI. While several promising methods …

The privacy of machine learning models has become a significant concern in many
emerging Machine-Learning-as-a-Service applications, where prediction services based on …

Deep neural networks (DNN) are widely used in real-life applications despite the lack of
understanding on this technology and its challenges. Data privacy is one of the bottlenecks …