Project description
Novel encryption and memory technology support more secure deep learning workloads
With the explosion of data available to enhance the accuracy of solutions to complex classification problems, deep learning methodologies have been instrumental in extracting features. However, together with increasing data availability has come the increasing need for data protection in the face of a growing rank of rogue actors with malicious intent. Integrating deep learning algorithms with encryption has been severely limited by the vast increase in data size of such algorithms combined with the limited memory available. The EU-funded HomE project will inspire a new class of system architectures for encrypted deep learning workloads, enabling hundreds of models to be run simultaneously with high resolution and accuracy.
Objective
Deep learning (DL) is widely used to solve classification problems previously unchallenged, such as face recognition, and presents clear use cases for privacy requirements. Homomorphic encryption (HE) enables operations upon encrypted data, at the expense of vast data size increase. RAM sizes currently limit the use of HE on DL to severely reduced use cases. Recently emerged persistent memory technology (PMEM) offers larger-than-ever RAM spaces, but its performance is far from that of customary DRAM technologies. This project aims at sparking a new class of system architectures for encrypted DL workloads, by eliminating or dramatically reducing data movements across memory/storage hierarchies and network, supported by PMEM technology, overcoming its current severe performance limitations. HomE intends to be a first-time enabler for the encrypted execution of large models that do not fit in DRAM footprints to execute local to accelerators, hundreds of DL models to run simultaneously, and large datasets to be run at high resolution and accuracy. Targeting these ground-breaking goals, HomE enters into unexplored field resulting from the innovative convergence of several disciplines, where wide-ranging research is required in order to assess current and future feasibility. Its main challenge is to develop methodology capable of breaking through the existing software and hardware limitations. HomE proposes a holistic approach yielding highly impactful outcomes that include novel comprehensive performance characterisation, innovative optimisations upon current technology, and pioneering hardware proposals. HomE can spawn a paradigm shift that will revolutionise the convergence of the machine learning and cryptography disciplines, filling a gap of knowledge and opening new horizons such as DL training on HE, currently too demanding even for DRAM. HomE, based on solid evidence, will unveil the great unknown of whether PMEM is a practical enabler for encrypted DL workloads.
Fields of science
- natural sciencescomputer and information sciencessoftware
- natural sciencescomputer and information sciencescomputer securitycryptography
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
- natural sciencescomputer and information sciencesartificial intelligencepattern recognition
Programme(s)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Funding Scheme
HORIZON-AG - HORIZON Action Grant Budget-BasedHost institution
08034 Barcelona
Spain