FlexBNN: Fast Private Binary Neural Network Inference With Flexible Bit-Width

Ye Dong, Xiaojun Chen, Xiangfu Song, Kaiyun Li

Abstract: Advancements in deep learning enable neural network (NN) inference to be a service, but service providers and clients want to keep their inputs secret for privacy protection. Private Inference is the task of evaluating NN without leaking private inputs. Existing secure multiparty computation (MPC)-based solutions mainly focus on fixed bit-width methodology, such as 32 and 64 bits. Binary Neural Network (BNN) is efficient when evaluated in MPC and has achieved reasonable accuracy for commonly used datasets, but prior private BNN inference solutions, which focus on Boolean Circuits, are still costly in communication and run-time. In this paper, we introduce FLEX BNN, a fast private BNN inference framework using three-party computation (3PC) in Arithmetic Circuits against semi-honest adversaries with honest-majority. In FLEX BNN, we propose to employ flexible and small bit-width equipped with a seamless bit-width conversion method and design several specific optimizations towards the basic operations: i) We propose bit-width determination methods for Matrix Multiplication and Sign-based Activation function. ii) We integrate Batch Normalization and Max-Pooling into the Sign-based Activation function for better efficiency. iii) More importantly, we achieve seamless bit-width conversion within the Sign-based Activation function with no additional cost. Extensive experiments illustrate that FLEX BNN outperforms state-of-the-art solutions in communication, run-time, and scalability. On average, FLEX BNN is <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$11\times $ </tex-math></inline-formula> faster than XONN (USENIX Security’19) in LAN, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$46\times $ </tex-math></inline-formula> (resp. <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$9.3\times $ </tex-math></inline-formula> ) faster than QUOTIENT (ACM CCS’19) in LAN (resp. WAN), <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$10\times $ </tex-math></inline-formula> faster than BANNERS (ACM IH&MMSec’21) in LAN, and 1.1- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2.9\times $ </tex-math></inline-formula> (resp. 1.5- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2.7\times $ </tex-math></inline-formula> ) faster than FALCON (semi-honest, PoPETs’21) in LAN (resp. WAN), and improves the respective communication by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$500\times $ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$127\times $ </tex-math></inline-formula> , and 1.3- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1.5\times $ </tex-math></inline-formula> compared to XONN, BANNERS, and FALCON.