【Author】
Li, Zonghang; Yu, Hongfang; Zhou, Tianyao; Luo, Long; Fan, Mochan; Xu, Zenglin; Sun, Gang
【Abstract】The emerging blockchained federated learning, known for its security properties such as decentralization, immutability and traceability, is evolving into an important direction of next-generation AI. With the booming edge computing technologies, blockchained federated learning can take advantage of computing, communication and storage resources geo-distributed at the edge, so that blockchained federated learning can gather edge intelligence from more widely distributed devices more efficiently. However, untrustworthy devices at the edge also bring serious security threats, namely byzantine attacks. Existing solutions focus on selecting local models that are most likely to be honest, rather than detecting byzantine models and identifying attackers, because verifying each local model separately brings intolerable verification delay. In this paper, we propose a byzantine resistant secure blockchained federated learning framework named BytoChain. BytoChain improves the efficiency of model verification by introducing verifiers to execute heavy verification workflows in parallel, and detects byzantine attacks through a byzantine resistant consensus Proof-of-Accuracy (PoA). We analyze how BytoChain can mitigate five types of attacks, and demonstrate its effectiveness by simulations. Finally, we envision some open issues about security, including attacks on privacy, confidentiality, and backdoors.
【Keywords】Training; Servers; Data models; Image edge detection; Blockchain; Biological system modeling; Security
【摘要】新兴的区块链联邦学习以其去中心化、不变性和可追溯性等安全特性而著称，正在演变为下一代人工智能的重要方向。随着边缘计算技术的蓬勃发展，区块链联邦学习可以利用地理分布在边缘的计算、通信和存储资源，使区块链联邦学习可以更有效地从分布更广泛的设备中收集边缘情报。然而，边缘的不可信设备也带来了严重的安全威胁，即拜占庭攻击。现有的解决方案侧重于选择最有可能诚实的本地模型，而不是检测拜占庭模型和识别攻击者，因为单独验证每个本地模型会带来无法容忍的验证延迟。在本文中，我们提出了一个名为 BytoChain 的抗拜占庭安全区块链联邦学习框架。 BytoChain 通过引入验证者并行执行繁重的验证工作流来提高模型验证的效率，并通过抗拜占庭共识 PoA 来检测拜占庭攻击。我们分析了 BytoChain 如何缓解五种类型的攻击，并通过模拟证明其有效性。最后，我们设想了一些关于安全的公开问题，包括对隐私、机密性和后门的攻击。
【关键词】训练;服务器；数据模型；图像边缘检测；区块链；生物系统建模；安全
评论