arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.26781cs.CRcs.LG
收藏

在卷积脉冲神经网络中实现高效的加密计算:TFHE

Efficient Encrypted Computation in Convolutional Spiking Neural Networks with TFHE

School of Cyber Science and Engineering, Huazhong University of Science and Technology(华中科技大学网络空间安全学院);School of Mathematics and Statistics, Huazhong University of Science and Technology(华中科技大学数学与统计学院);Center for Mathematical Science, Huazhong University of Science and Technology(华中科技大学数学中心);Steklov-Wuhan Institute for Mathematical Exploration, Huazhong University of Science and Technology(华中科技大学斯捷克洛夫-武汉数学探索研究所);Department of Mathematics and Department of Physics, Great Bay University(大湾区大学数学与物理学院);Guangdong Provincial Key Laboratory of Mathematical and Neural Dynamical Systems(广东省数学与神经动力系统重点实验室)

Longfei Guo, Pengbo Li, Ting Gao, Yonghai Zhong, Haojie Fan, Jinqiao Duan

AI总结:

本文提出FHE-DiCSNN框架,利用脉冲神经网络的离散特性实现安全高效的加密计算,结合卷积方法提升准确率并减少模拟时间,实验验证其在MNIST和FashionMNIST上的有效性。

摘要:

随着AI技术的快速发展,数据隐私问题日益受到关注,促使机器学习领域开展加密计算研究。全同态加密(FHE)是隐私保护计算的关键技术,但其在处理连续非多项式函数时存在困难,因其基于离散整数并仅支持加法和乘法。脉冲神经网络(SNNs)使用离散脉冲信号,与FHE特性互补。本文提出FHE-DiCSNN框架,基于TFHE方案,利用SNNs的离散特性实现安全高效的计算。通过利用提升技术,成功在密文上实现Leaky Integrate-and-Fire(LIF)神经元模型,允许任意深度的SNNs。该框架可适应其他脉冲神经元模型,提供了一种新颖的同态评估SNNs的方法。此外,我们整合受CNN启发的卷积方法,以提高精度并减少随机编码相关的模拟时间。并行计算技术进一步加速了提升操作。在MNIST和FashionMNIST数据集上的实验结果验证了FHE-DiCSNN的有效性,其损失分别低于纯文本3%,且每预测时间不足1秒。我们还将其应用于实际的医疗图像分类问题,并分析了参数优化和选择。

英文摘要:

With the rapid advancement of AI technology, we have seen more and more concerns on data privacy, leading to some cutting-edge research on machine learning with encrypted computation. Fully Homomorphic Encryption (FHE) is a crucial technology for privacy-preserving computation, while it struggles with continuous non-polynomial functions, as it operates on discrete integers and supports only addition and multiplication. Spiking Neural Networks (SNNs), which use discrete spike signals, naturally complement FHE's characteristics. In this paper, we introduce FHE-DiCSNN, a framework built on the TFHE scheme, utilizing the discrete nature of SNNs for secure and efficient computations. By leveraging bootstrapping techniques, we successfully implement Leaky Integrate-and-Fire (LIF) neuron models on ciphertexts, allowing SNNs of arbitrary depth. Our framework is adaptable to other spiking neuron models, offering a novel approach to homomorphic evaluation of SNNs. Additionally, we integrate convolutional methods inspired by CNNs to enhance accuracy and reduce the simulation time associated with random encoding. Parallel computation techniques further accelerate bootstrapping operations. Experimental results on the MNIST and FashionMNIST datasets validate the effectiveness of FHE-DiCSNN, with a loss of less than 3\% compared to plaintext, respectively, and computation times of under 1 second per prediction. We also apply the model into real medical image classification problems and analyze the parameter optimization and selection.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑