Privacy Preserving In-memory Computing Engine

TL;DR

PPIMCE is an in-memory computing fabric that significantly accelerates privacy-preserving computations like homomorphic encryption and garbled circuits, reducing overhead and enabling efficient privacy-preserving machine learning inference.

Contribution

The paper introduces PPIMCE, a novel in-memory computing architecture that mitigates computational and data transfer bottlenecks in privacy-preserving cryptographic techniques.

Findings

Achieves 107X speedup over CPU for garbled circuits.

Attains 1,500X and 800X speedup over CPU and GPU for HE multiplications.

Provides 1,000X speedup in privacy-preserving ML inference compared to CPU.

Abstract

Privacy has rapidly become a major concern/design consideration. Homomorphic Encryption (HE) and Garbled Circuits (GC) are privacy-preserving techniques that support computations on encrypted data. HE and GC can complement each other, as HE is more efficient for linear operations, while GC is more effective for non-linear operations. Together, they enable complex computing tasks, such as machine learning, to be performed exactly on ciphertexts. However, HE and GC introduce two major bottlenecks: an elevated computational overhead and high data transfer costs. This paper presents PPIMCE, an in-memory computing (IMC) fabric designed to mitigate both computational overhead and data transfer issues. Through the use of multiple IMC cores for high parallelism, and by leveraging in-SRAM IMC for data management, PPIMCE offers a compact, energy-efficient solution for accelerating HE and GC. PPIMCE achieves a 107X speedup against a CPU implementation of GC. Additionally, PPIMCE achieves a 1,500X and 800X speedup compared to CPU and GPU implementations of CKKS-based HE multiplications. For privacy-preserving machine learning inference, PPIMCE attains a 1,000X speedup compared to CPU and a 12X speedup against CraterLake, the state-of-art privacy preserving computation accelerator.