Secure Distributed Computation for Federated Learning and Blockchains

讲座名称：Secure Distributed Computation for Federated Learning and Blockchains

讲座人：Songze LI

讲座时间：5月29日15:00

地点：亚博足彩新科1012

讲座人介绍：

李松泽是香港科技大学（广州）物联网方向和人工智能方向的助理教授，也是香港科技大学计算机科学系的助理教授。在2020年加入香港科技大学之前，他曾在斯坦福大学担任过两年的区块链研究员。于2011年在纽约大学获得学士学位，并于2018年在南加利福尼亚大学获得博士学位，均为电子工程专业。目前主要研究领域包括人工智能安全与隐私、安全的多方计算及隐私以及区块链的安全性和可扩展性。目前担任两个国际信息理论和信息安全期刊的客座编辑，还担任了14个人工智能和通信领域的顶级国际期刊和会议的TPC成员。在NeurIPS-20 Workshop on Scalability，Privacy，and Security in Federated Learning上获得了最佳论文奖。2017年高通创新奖学金的入围者。

讲座内容：

Security and privacy issues are becoming increasingly critical to the development anddeployment of modern information systems. This talk provides an overview on ourrecent results of developing secure, robust, and efficient distributed computationprotocols, for the application of federated learning (FL) and blockchains. Two thingswill be discussed.Federated Learning:We expose the vulnerability of FL models via developing a novel backdoor attack that significantly improve the backdoor durability over SOTA; we develop novel secure model aggregation protocols that respectivelyminimizes the computation and communication overhead, while providinginformation-theoretic privacy for clients’ data; we also develop secure model/embedding aggregation protocols for horizontal and vertical FL scenarios, simultaneously achieving lossless performance and perfect privacy in presence of client dropouts.Blockchains:We propose coded Merkle tree, a novel cryptographic accumulator that allows a blockchain light client to securely and efficiently verify the availability of a block; we also develop PolyShard, a novel blockchain sharding protocol that leverages coded computation to simultaneously scale the storage efficiency, throughput, and security of block verification, in presence of adaptive adversaries.

主办单位：空天地一体化综合业务网全国重点实验室