Trustworthy Federated Learning Against Malicious Attacks in Web 3.0
【Author】 Yuan, Zheng; Tian, Youliang; Zhou, Zhou; Li, Ta; Wang, Shuai; Xiong, Jinbo
【Source】IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
【影响因子】5.033
【Abstract】In the era of Web 3.0, federated learning has emerged as a crucial technical method in resolving conflicts between data security and open sharing. However, federated learning is susceptible to various malicious behaviors, including inference attacks, poisoning attacks, and free-riding attacks. These adversarial activities can lead to privacy breaches, unavailability of global models, and unfair training processes. To tackle these challenges, we propose a trustworthy federated learning scheme (TWFL) that can resist the above malicious attacks. Specifically, we firstly propose a novel adaptive method based on two-trapdoor homomorphic encryption to encrypt gradients uploaded by users, thereby resisting inference attacks. Secondly, we design confidence calculation and contribution calculation mechanisms to resist poisoning attacks and free-riding attacks. Finally, we prove the security of our scheme through formal security analysis, and demonstrate through experiments conducted on MNIST and FASHIONMNIST datasets that TWFL achieves a higher model accuracy of 2%-3% compared to traditional methods such as Median and Trim-mean. In summary, TWFL can not only resist a variety of attacks but also ensure improved accuracy, which is enough to prove that it is a trustworthy solution suitable for Web 3.0 privacy protection scenarios.
【Keywords】Federated learning; Training; Semantic Web; Servers; Privacy; Blockchains; Resists; web 3.0; inference attacks; poisoning attacks; free-riding attacks
【发表时间】2024 SEP
【收录时间】2024-09-24
【文献类型】实验仿真
【主题类别】
区块链技术-协同技术-联邦学习
评论