Practical, Private Assurance of the Value of Collaboration via Fully Homomorphic Encryption
作者: Hassan Jameel Asghar, Zhigang Lu, Zhongrui Zhao, Dali Kaafar
分类: cs.CR, cs.LG
发布日期: 2023-10-04 (更新: 2024-10-07)
备注: This is the full version of the paper accepted for publication in the Proceedings on the 25th Privacy Enhancing Technologies Symposium (PoPETs) 2025
💡 一句话要点
提出基于全同态加密的协作价值保障方案
🎯 匹配领域: 支柱五:交互与反应 (Interaction & Reaction)
关键词: 全同态加密 差分隐私 机器学习 数据共享 隐私保护
📋 核心要点
- 核心问题:现有方法在保护数据隐私的同时,难以确保合作的有效性,导致双方不愿意共享数据。
- 方法要点:提出了一种基于全同态加密和标签差分隐私的交互协议,使得双方可以在不泄露数据的情况下评估模型的准确性。
- 实验或效果:实验结果显示,该协议在计算效率上比完全依赖全同态加密的协议快多个数量级,具有显著的实用性。
📝 摘要(中文)
两方希望在不泄露各自数据集的情况下进行合作,但在此之前希望确保合作能够带来实际的收益。本文从机器学习的角度出发,构建了一种基于全同态加密(TFHE)和标签差分隐私的交互协议。该协议允许一方在未完全公开数据集和模型的情况下,评估通过引入另一方数据集后模型的准确性提升。我们在假设诚实但好奇的参与者的前提下,形式化证明了该方案的安全性,并通过实验表明,与完全依赖全同态加密操作的协议相比,输出结果的时间效率提升了多个数量级。
🔬 方法详解
问题定义:本文旨在解决在数据隐私保护下,如何确保两方合作能带来模型准确性提升的问题。现有方法通常需要完全公开数据集,导致隐私风险和合作意愿降低。
核心思路:通过构建一个基于全同态加密的交互协议,结合标签差分隐私,允许双方在不完全公开数据的情况下评估模型的改进效果,从而降低隐私泄露风险。
技术框架:整体架构包括数据加密、模型训练和准确性评估三个主要模块。首先,双方对各自数据进行加密,然后在加密域内进行模型训练,最后通过协议评估更新后的模型准确性。
关键创新:最重要的创新点在于结合了全同态加密与标签差分隐私,允许部分计算在明文域进行,从而克服了传统全同态加密在神经网络训练中的性能瓶颈。
关键设计:在协议设计中,采用了适当的参数设置以平衡隐私保护与计算效率,同时选择了适合的损失函数和网络结构,以确保模型训练的有效性。
🖼️ 关键图片
📊 实验亮点
实验结果表明,使用该协议可以在多个数量级上提升计算效率,相较于完全依赖全同态加密的协议,输出结果的时间显著缩短,展示了其在实际应用中的可行性和优势。
🎯 应用场景
该研究的潜在应用领域包括医疗数据共享、金融数据分析和跨组织合作等场景,能够在保护数据隐私的同时,促进数据驱动的决策和创新。未来,该方法有望在更多领域推广,推动数据合作的普及。
📄 摘要(原文)
Two parties wish to collaborate on their datasets. However, before they reveal their datasets to each other, the parties want to have the guarantee that the collaboration would be fruitful. We look at this problem from the point of view of machine learning, where one party is promised an improvement on its prediction model by incorporating data from the other party. The parties would only wish to collaborate further if the updated model shows an improvement in accuracy. Before this is ascertained, the two parties would not want to disclose their models and datasets. In this work, we construct an interactive protocol for this problem based on the fully homomorphic encryption scheme over the Torus (TFHE) and label differential privacy, where the underlying machine learning model is a neural network. Label differential privacy is used to ensure that computations are not done entirely in the encrypted domain, which is a significant bottleneck for neural network training according to the current state-of-the-art FHE implementations. We formally prove the security of our scheme assuming honest-but-curious parties, but where one party may not have any expertise in labelling its initial dataset. Experiments show that we can obtain the output, i.e., the accuracy of the updated model, with time many orders of magnitude faster than a protocol using entirely FHE operations.