With the rapid development of low-cost consumer electronics and pervasive adoption of next
generation wireless communication technologies, a tremendous amount of data has been …

The widespread adoption of deep learning is facilitated in part by the availability of large-
scale data for training desirable models. However, these data may involve sensitive …

The objective of differential privacy (DP) is to protect privacy by producing an output
distribution that is indistinguishable between any two neighboring databases. However …

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 …

Vector mean estimation is a central primitive in federated analytics. In vector mean
estimation, each user i∈n holds a real-valued vector v_i∈-1,1^d, and a server wants to …

Many applications rely on continual data collection to provide real-time information services,
eg, real-time road traffic forecasts. However, the collection of original data brings risks to …

The protocols that satisfy Local Differential Privacy (LDP) enable untrusted third parties to
collect aggregate information about a population without disclosing each user's privacy. In …

Local differential privacy (LDP), which perturbs each user's data locally and only sends the
noisy version of her information to the aggregator, is a popular privacy-preserving data …

While collecting data from a large population, local differential privacy (LDP), which only
sends users' perturbed data to the data collector, becomes a popular solution to preserving …

Between the changing Industry 4.0 landscape and the rise of Industry 5.0, where human
intelligence and intelligent machines work together, vast amounts of privacy-sensitive data …