Yue Wenshuo, Wu Kai, Li Zhiyuan, Zhou Juchen, Wang Zeyu, Zhang Teng, Yang Yuxiang, Ye Lintao, Wu Yongqin, Bu Weihai, Wang Shaozhi, He Xiaodong, Yan Xiaobing, Tao Yaoyu, Yan Bonan, Huang Ru, Yang Yuchao
Beijing Advanced Innovation Center for Integrated Circuits, School of Integrated Circuits, Peking University, Beijing, China.
Institute for Artificial Intelligence, Peking University, Beijing, China.
Nat Commun. 2025 Jan 25;16(1):1031. doi: 10.1038/s41467-025-56412-w.
Compute-in-memory based on resistive random-access memory has emerged as a promising technology for accelerating neural networks on edge devices. It can reduce frequent data transfers and improve energy efficiency. However, the nonvolatile nature of resistive memory raises concerns that stored weights can be easily extracted during computation. To address this challenge, we propose RePACK, a threefold data protection scheme that safeguards neural network input, weight, and structural information. It utilizes a bipartite-sort coding scheme to store data with a fully on-chip physical unclonable function. Experimental results demonstrate the effectiveness of increasing enumeration complexity to 5.77 × 10 for a 128-column compute-in-memory core. We further implement and evaluate a RePACK computing system on a 40 nm resistive memory compute-in-memory chip. This work represents a step towards developing safe, robust, and efficient edge neural network accelerators. It potentially serves as the hardware infrastructure for edge devices in federated learning or other systems.
基于电阻式随机存取存储器的内存计算已成为一种很有前途的技术，可用于加速边缘设备上的神经网络。它可以减少频繁的数据传输并提高能源效率。然而，电阻式存储器的非易失性引发了人们的担忧，即存储的权重在计算过程中可能很容易被提取。为应对这一挑战，我们提出了RePACK，这是一种三重数据保护方案，可保护神经网络的输入、权重和结构信息。它利用二分排序编码方案，通过完全片上物理不可克隆功能来存储数据。实验结果表明，对于一个128列的内存计算核心，枚举复杂度提高到了5.77×10。我们还在一个40纳米的电阻式内存计算芯片上实现并评估了一个RePACK计算系统。这项工作朝着开发安全、稳健且高效的边缘神经网络加速器迈出了一步。它有可能成为联邦学习或其他系统中边缘设备的硬件基础设施。
