Bicoptor 2.0: Addressing Challenges in Probabilistic Truncation for Enhanced Privacy-Preserving Machine Learning

TL;DR

This paper analyzes and corrects probabilistic truncation issues in PPML, introduces deterministic truncation and security protocols, and achieves significant performance improvements in privacy-preserving ML inference.

Contribution

It provides a theoretical correction for probabilistic truncation, proposes a non-interactive deterministic truncation protocol, and enhances PPML efficiency with key bit optimization.

Findings

10x faster DReLU protocol

6x faster ReLU protocol

3-4 times overall PPML performance improvement

Abstract

This paper primarily focuses on analyzing the problems and proposing solutions for the probabilistic truncation protocol in existing PPML works from the perspectives of accuracy and efficiency. In terms of accuracy, we reveal that precision selections recommended in some of the existing works are incorrect. We conduct a thorough analysis of their open-source code and find that their errors were mainly due to simplified implementation, more specifically, fixed numbers are used instead of random numbers in probabilistic truncation protocols. Based on this, we provide a detailed theoretical analysis to validate our views. We propose a solution and a precision selection guideline for future works. Regarding efficiency, we identify limitations in the state-of-the-art comparison protocol, Bicoptor's (S\&P 2023) DReLU protocol, which relies on the probabilistic truncation protocol and is heavily constrained by the security parameter to avoid errors, significantly impacting the protocol's performance. To address these challenges, we introduce the first non-interactive deterministic truncation protocol, replacing the original probabilistic truncation protocol. Additionally, we design a non-interactive modulo switch protocol to enhance the protocol's security. Finally, we provide a guideline to reduce computational and communication overhead by using only a portion of the bits of the input, i.e., the key bits, for DReLU operations based on different model parameters. With the help of key bits, the performance of our DReLU protocol is further improved. We evaluate the performance of our protocols on three GPU servers, and achieve a 10x improvement in DReLU protocol, and a 6x improvement in the ReLU protocol over the state-of-the-art work Piranha-Falcon (USENIX Sec 22). Overall, the performance of our end-to-end (E2E) privacy-preserving machine learning (PPML) inference is improved by 3-4 times.