Enabling Low-Cost Secure Computing on Untrusted In-Memory Architectures

2025-01-28

AI Summary

Sensitive data off-chip transmission in Processing-in-Memory (PIM) architectures undermines the Trusted Computing Base (TCB), creating a critical security bottleneck for confidential computing. Method: We propose the first co-designed confidential computing framework integrating Multi-Party Computation (MPC) with PIM—unifying arithmetic secret sharing and Yao’s garbled circuits—and introduce precomputation optimizations to offload MPC overhead from the CPU. Contribution/Results: Implemented on the UPMEM PIM platform, our solution enables high-bandwidth, low-overhead secure outsourced computation while strictly guaranteeing data confidentiality and integrity. Experiments on recommendation model inference and logistic regression demonstrate up to 14.66× speedup over secure CPU-only baselines, effectively breaking the longstanding trade-off between security and performance under the memory wall.

Technology Category

• Machine Learning: Hardware-aware ML
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: (Computational) Cognitive Architectures

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

Modern computing systems are limited in performance by the memory bandwidth available to processors, a problem known as the memory wall. Processing-in-Memory (PIM) promises to substantially improve this problem by moving processing closer to the data, improving effective data bandwidth, and leading to superior performance on memory-intensive workloads. However, integrating PIM modules within a secure computing system raises an interesting challenge: unencrypted data has to move off-chip to the PIM, exposing the data to attackers and breaking assumptions on Trusted Computing Bases (TCBs). To tackle this challenge, this paper leverages multi-party computation (MPC) techniques, specifically arithmetic secret sharing and Yao's garbled circuits, to outsource bandwidth-intensive computation securely to PIM. Additionally, we leverage precomputation optimization to prevent the CPU's portion of the MPC from becoming a bottleneck. We evaluate our approach using the UPMEM PIM system over various applications such as Deep Learning Recommendation Model inference and Logistic Regression. Our evaluations demonstrate up to a $14.66 imes$ speedup compared to a secure CPU configuration while maintaining data confidentiality and integrity when outsourcing linear and/or nonlinear computation.

Problem

• Data Security
• In-Memory Processing
• Performance Efficiency

Innovation

• PIM Architecture
• Advanced Encryption
• Performance Optimization