Barcelona Supercomputing Center Powers Encrypted Neural Networks with Intel Tech
Homomorphic encryption provides two extraordinary benefits: first, it has the potential to be secure against intrusion by even quantum computers; second, it allows users to use the data for computation without necessitating decryption, enabling offload of secure data to commercial clouds and other external locations. However – as researchers from Intel and the Barcelona Supercomputing Center (BSC) explained – homomorphic encryption “is not exempt from drawbacks that render it currently impractical in many scenarios,” including that “the size of the data increases fiercely when encrypted,” limiting its application for large neural networks.
Now, that might be changing: BSC and Intel have, for the first time, executed homomorphically encrypted large neural networks.
“Homomorphic encryption … enables inference using encrypted data but it incurs 100x–10,000x memory and runtime overheads,” the authors wrote in their paper. “Secure deep neural network … inference using [homomorphic encryption] is currently limited by computing and memory resources, with frameworks requiring hundreds of gigabytes of DRAM to evaluate small models.”
To do that, the researchers deployed Intel tech: specifically, Intel Optane persistent memory and Intel Xeon Scalable processors. The Optane memory was combined with DRAM to supplement the higher capacity of persistent memory with the faster speeds of DRAM. They tested the combination using a variety of different configurations to run large neural networks, including ResNet-50 (now the largest neural network ever run using homomorphic encryption) and the largest variant of MobileNetV2. Following the experiments, they landed on a configuration with just a third of the DRAM – but only a 10 percent drop in performance relative to a full-DRAM system.
“This new technology will allow the general use of neural networks in cloud environments, including, for the first time, where indisputable confidentiality is required for the data or the neural network model,” said Antonio J. Peña, the BSC researcher who led the study and head of BSC’s Accelerators and Communications for High Performance Computing Team.
“The computation is both compute-intensive and memory-intensive,” added Fabian Boemer, a technical lead at Intel supporting this research. “To speed up the bottleneck of memory access, we are investigating different memory architectures that allow better near-memory computing. This work is an important first step to solving this often-overlooked challenge. Among other technologies, we are investigating the use [of] Intel Optane persistent memory to keep constantly accessed data close to the processor during the evaluation.”
To learn more about this research, read the research paper, which is available in full here.
April 26, 2024
- Google Announces $75M AI Opportunity Fund and New Course to Skill One Million Americans
- Elastic Reports 8x Speed and 32x Efficiency Gains for Elasticsearch and Lucene Vector Database
- Gartner Identifies the Top Trends in Data and Analytics for 2024
- Satori and Collibra Accelerate AI Readiness Through Unified Data Management
- Argonne’s New AI Application Reduces Data Processing Time by 100x in X-ray Studies
April 25, 2024
- Salesforce Unveils Zero Copy Partner Network, Offering New Open Data Lake Access via Apache Iceberg
- Dataiku Enables Generative AI-Powered Chat Across the Enterprise
- IBM Transforms the Storage Ownership Experience with IBM Storage Assurance
- Cleanlab Launches New Solution to Detect AI Hallucinations in Language Models
- University of Maryland’s Smith School Launches New Center for AI in Business
- SAS Advances Public Health Research with New Analytics Tools on NIH Researcher Workbench
- NVIDIA to Acquire GPU Orchestration Software Provider Run:ai
April 24, 2024
- AtScale Introduces Developer Community Edition for Semantic Modeling
- Domopalooza 2024 Sets a High Bar for AI in Business Intelligence and Analytics
- BigID Highlights Crucial Security Measures for Generative AI in Latest Industry Report
- Moveworks Showcases the Power of Its Next-Gen Copilot at Moveworks.global 2024
- AtScale Announces Next-Gen Product Innovations to Foster Data-Driven Industry-Wide Collaboration
- New Snorkel Flow Release Empowers Enterprises to Harness Their Data for Custom AI Solutions
- Snowflake Launches Arctic: The Most Open, Enterprise-Grade Large Language Model
- Lenovo Advances Hybrid AI Innovation to Meet the Demands of the Most Compute Intensive Workloads
Most Read Features
Sorry. No data so far.
Most Read News In Brief
Sorry. No data so far.
Most Read This Just In
Sorry. No data so far.
Sponsored Partner Content
-
Get your Data AI Ready – Celebrate One Year of Deep Dish Data Virtual Series!
-
Supercharge Your Data Lake with Spark 3.3
-
Learn How to Build a Custom Chatbot Using a RAG Workflow in Minutes [Hands-on Demo]
-
Overcome ETL Bottlenecks with Metadata-driven Integration for the AI Era [Free Guide]
-
Gartner® Hype Cycle™ for Analytics and Business Intelligence 2023
-
The Art of Mastering Data Quality for AI and Analytics
Sponsored Whitepapers
Contributors
Featured Events
-
AI & Big Data Expo North America 2024
June 5 - June 6Santa Clara CA United States -
CDAO Canada Public Sector 2024
June 18 - June 19 -
AI Hardware & Edge AI Summit Europe
June 18 - June 19London United Kingdom -
AI Hardware & Edge AI Summit 2024
September 10 - September 12San Jose CA United States -
CDAO Government 2024
September 18 - September 19Washington DC United States