Projektbeschreibung
Neuartige Verschlüsselungs- und Speichertechnologie für mehr Sicherheit bei der Nutzung von Deep Learning
Mit der explosionsartigen Zunahme der verfügbaren Daten zur Verbesserung der Lösungsgenauigkeit bei komplexen Klassifizierungsproblemen haben sich Methoden des Deep Learning als hilfreich bei der Extraktion von Eigenschaften erwiesen. Mit der zunehmenden Verfügbarkeit von Daten steigt jedoch auch der Bedarf für deren Schutz angesichts der wachsenden Zahl krimineller Gruppen mit böswilligen Absichten. Die Integration von Deep-Learning-Algorithmen mit Verschlüsselung war bisher durch die enorme Zunahme der Datengröße solcher Algorithmen in Verbindung mit dem begrenzten verfügbaren Speicher stark eingeschränkt. Das EU-finanzierte Projekt HomE wird eine neue Klasse von Systemarchitekturen für verschlüsselte Deep-Learning-Arbeitslasten inspirieren, die es ermöglichen, Hunderte von Modellen gleichzeitig mit hoher Auflösung und Genauigkeit auszuführen.
Ziel
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.
Wissenschaftliches Gebiet
- 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
Programm/Programme
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Thema/Themen
Finanzierungsplan
HORIZON-AG - HORIZON Action Grant Budget-BasedGastgebende Einrichtung
08034 Barcelona
Spanien