Federated learning enables multiple data owners to jointly train a machine learning model without revealing their private datasets. However, a malicious aggregation server might use the model parameters to derive sensitive information about the training dataset used. To address such leakage, differential privacy and cryptographic techniques have been investigated in prior work, but these often result in large communication overheads or impact model performance. To mitigate this centralization of power, we propose SCOTCH, a decentralized m-party secure-computation framework for federated aggregation that deploys MPC primitives, such as secret sharing. Our protocol is simple, efficient, and provides strict privacy guarantees against curious aggregators or colluding data-owners with minimal communication overheads compared to other existing state-of-the-art privacy-preserving federated learning frameworks. We evaluate our framework by performing extensive experiments on multiple datasets with promising results. SCOTCH can train the standard MLP NN with the training dataset split amongst 3 participating users and 3 aggregating servers with 96.57% accuracy on MNIST, and 98.40% accuracy on the Extended MNIST (digits) dataset, while providing various optimizations.
翻译:联邦学习使多个数据拥有者能够在不透露其私人数据集的情况下联合培训机器学习模型。 但是,恶意聚集服务器可能会使用模型参数来获取关于所使用培训数据集的敏感信息。 为了解决这种泄漏、差异隐私和加密技术在先前工作中已经调查过,但这些技术往往导致大量的通信间接费用或影响模型性能。为了减轻这种权力集中化,我们提议SCCCHT(一个分散的M-part安全计算框架),用于联邦汇总,以部署MPC原始产品,如秘密共享。我们的协议简单、高效,并提供严格的隐私保障,防止好奇的聚合者或串通数据拥有者与现有的其他最先进的保密联合学习框架相比,通信管理费用极低。我们通过对多数据集进行广泛的实验,并取得有希望的结果。 SCCCHT可以培训标准 MLP NNN,将培训数据集分成3个参与的用户和3个综合服务器,其精确度达到96.57%的MNIST,同时提供各种优化。