Description du projet
Une nouvelle technologie de chiffrement et de mémoire permet de sécuriser davantage les charges de travail d’apprentissage profond
Face à l’explosion des données disponibles pour améliorer la précision des solutions aux problèmes de classification complexes, les méthodologies d’apprentissage profond ont été déterminantes pour l’extraction de caractéristiques. Cependant, la disponibilité croissante des données s’accompagne d’un besoin accru de protection de ces données face à un nombre croissant d’acteurs malveillants. L’intégration des algorithmes d’apprentissage profond avec le chiffrement a été fortement limitée par l’augmentation considérable de la taille des données de ces algorithmes combinée à la limitation de la mémoire disponible. Le projet HomE, financé par l’UE, inspirera une nouvelle catégorie d’architectures de système pour les charges de travail d’apprentissage profond chiffrées, permettant d’exécuter simultanément des centaines de modèles avec une résolution et une précision élevées.
Objectif
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.
Champ scientifique
- 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
Régime de financement
HORIZON-AG - HORIZON Action Grant Budget-BasedInstitution d’accueil
08034 Barcelona
Espagne