Differential Privacy has become a widely popular method for data protection in machine
learning, especially since it allows formulating strict mathematical privacy guarantees. This …

With the proliferation of Beyond 5G (B5G) communication systems and heterogeneous
networks, mobile broadband users are generating massive volumes of data that undergo …

Deep learning models are often trained on datasets that contain sensitive information such
as individuals' shop** transactions, personal contacts, and medical records. An …

Federated learning is an effective technique to solve the problem of information fusion and
information sharing in intelligent vehicle networking. However, most of the existing federated …

Gradient leakage attacks are considered one of the wickedest privacy threats in deep
learning as attackers covertly spy gradient updates during iterative training without …

Machine learning models are known to memorize private data to reduce their training loss,
which can be inadvertently exploited by privacy attacks such as model inversion and …

Differentially private (DP) training preserves the data privacy usually at the cost of slower
convergence (and thus lower accuracy), as well as more severe mis-calibration than its non …

Membership inference attacks aim to detect if a particular data point was used in training a
model. We design a novel statistical test to perform robust membership inference attacks …

Motivated by the security risks of deep neural networks, such as various membership and
attribute inference attacks, differential privacy has emerged as a promising approach for …

In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in
adversarial learning for deep neural networks (DNNs), with certified robustness to …