Mobile Edge Computing (MEC) has great potential to facilitate cheap and fast customer
behavior analysis (CBA). Model splitting, widely adopted in collaborative learning of MEC …

We initiate a formal study on the concept of learnable obfuscation and aim to answer the
following question: is there a type of data encoding that maintains the" learnability" of …

The promise of least-privilege learning--to find feature representations that are useful for a
learning task but prevent inference of any sensitive information unrelated to this task--is …

Secure multi-party computation (MPC) allows users to offload machine learning inference on
untrusted servers without having to share their privacy-sensitive data. Despite their strong …

The increased complexity of nowadays common Machine Learning tasks and the availability
of ubiquitously connected devices initiated the current trend of shifting a substantial amount …

Distributed machine learning has become increasingly vital as devices generate vast
amounts of data. However, ensuring privacy during model synchronization represents a …