【Author】 Peng, Zhe; Xu, Jianliang; Chu, Xiaowen; Gao, Shang; Yao, Yuan; Gu, Rong; Tang, Yuzhe
【Source】IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
【Abstract】Advanced artificial intelligence techniques, such as federated learning, has been applied to broad areas, e.g., image classification, speech recognition, smart city, and healthcare. Despite intensive research on federated learning, existing schemes are vulnerable to attacks and can hardly meet the security requirements for real-world applications. The problem of designing a secure federated learning framework to ensure the correctness of training procedure has not been sufficiently studied and remains open. In this paper, we propose VFChain, a verifiable and auditable federated learning framework based on the blockchain system. First, to provide the verifiability, a committee is selected through the blockchain to collectively aggregate models and record verifiable proofs in the blockchain. Then, to provide the auditability, a novel authenticated data structure is proposed for blockchain to improve the search efficiency of verifiable proofs and support a secure rotation of committee. Finally, to further improve the search efficiency, an optimization scheme is proposed to support multiple-model learning tasks. We implement VFChain and conduct extensive experiments by utilizing the popular deep learning models over the public real-world dataset. The evaluation results demonstrate the effectiveness of our proposed VFChain system.
【Keywords】Blockchain; Collaborative work; Training; Data models; Servers; Computational modeling; Task analysis; Auditable training; blockchain; federated learning; model verification
【标题】VFChain:通过区块链系统实现可验证和可审计的联邦学习
【摘要】联邦学习等先进的人工智能技术已应用于广泛的领域,例如图像分类、语音识别、智慧城市和医疗保健。尽管对联邦学习进行了深入研究,但现有方案容易受到攻击,难以满足实际应用的安全要求。设计安全的联邦学习框架以确保训练过程的正确性的问题尚未得到充分研究并且仍然存在。在本文中,我们提出了 VFChain,一个基于区块链系统的可验证和可审计的联邦学习框架。首先,为了提供可验证性,通过区块链选择一个委员会来集体聚合模型并将可验证的证明记录在区块链中。然后,为了提供可审计性,为区块链提出了一种新颖的认证数据结构,以提高可验证证明的搜索效率并支持委员会的安全轮换。最后,为了进一步提高搜索效率,提出了一种支持多模型学习任务的优化方案。我们通过在公共现实世界数据集上利用流行的深度学习模型来实施 VFChain 并进行广泛的实验。评估结果证明了我们提出的 VFChain 系统的有效性。
【关键词】区块链;协作工作;训练;数据模型;服务器;计算建模;任务分析;可审计的培训;区块链;联邦学习;模型验证
【发表时间】2022
【收录时间】2022-07-06
【文献类型】Article
【论文大主题】区块链联邦学习
【论文小主题】联邦学习为主体
【影响因子】5.033
【翻译者】石东瑛
评论