Most of our lives are conducted in the cyberspace. The human notion of privacy translates
into a cyber notion of privacy on many functions that take place in the cyberspace. This …

The growth of the Machine-Learning-As-A-Service (MLaaS) market has highlighted clients'
data privacy and security issues. Private inference (PI) techniques using cryptographic …

Abstract The growth of Graph Convolution Network (GCN) model sizes has revolutionized
numerous applications, surpassing human performance in areas such as personal …

Machine Learning as a Service (MLaaS) allows clients with limited resources to outsource
their expensive ML tasks to powerful servers. Despite the huge benefits, current MLaaS …

We show that typical implicit regularization assumptions for deep neural networks (for
regression) do not hold for coordinate-MLPs, a family of MLPs that are now ubiquitous in …

Data privacy is of great concern in cloud machine-learning service platforms when sensitive
data are exposed to service providers. While private computing environments (eg secure …

The (gradient-based) bilevel programming framework is widely used in hyperparameter
optimization and has achieved excellent performance empirically. Previous theoretical work …

Stragglers, Byzantine workers, and data privacy are the main bottlenecks in distributed cloud
computing. Some prior works proposed coded computing strategies to jointly address all …

Fully Homomorphic Encryption (FHE) is a relatively recent advancement in the field of
privacy-preserving technologies. FHE allows for the arbitrary depth computation of both …

Lookup arguments allow to prove that the elements of a committed vector come from a
(bigger) committed table. They enable novel approaches to reduce the prover complexity of …