Modern cyber physical systems (CPSs) has widely being used in our daily lives because of
development of information and communication technologies (ICT). With the provision of …

The rapid evolution of the Internet of Things (IoT) paradigm during the last decade has lead
to its adoption in critical infrastructure. However, the multitude of benefits that are derived …

Deep Learning has recently become hugely popular in machine learning for its ability to
solve end-to-end learning systems, in which the features and the classifiers are learned …

High-dimensional crowdsourced data collected from numerous users produces rich
knowledge about our society; however, it also brings unprecedented privacy threats to the …

Many organizations stand to benefit from pooling their data together in order to draw
mutually beneficial insights—eg, for fraud detection across banks, better medical studies …

Multiparty computation as a service (MPSaaS) is a promising approach for building privacy-
preserving communication systems. However, in this paper, we argue that existing MPC …

Private learning of top-k, ie, the k most frequent values also called heavy hitters, is a
common industry scenario: Companies want to privately learn, eg, frequently typed new …

The massive generation, extensive sharing, and deep exploitation of data in the big data era
have raised unprecedented privacy threats. To address privacy concerns, various privacy …

We consider how to perform privacy-preserving analyses on private data from different data
providers and containing personal information of many different individuals. We combine …

Many applications of machine learning, for example in health care, would benefit from
methods that can guarantee privacy of data subjects. Differential privacy (DP) has become …