… However, there is the risk of single point failure with FL because it relies on a central server to gather the model updates from clients, moreover, maliciousbehaviors of some clients may …
… The transaction is a concept in blockchain system involving cryptocurrency, contracts, records or other information to record all behavior in blockchain. In this paper, we assume that the …
X Hei, X Yin, Y Wang, J Ren, L Zhu - Computers & Security, 2020 - Elsevier
… behavior on the blockchain. In order to solve the high probability of false alerts affecting the accuracy of the federatedlearning … principle of the federatedlearning and blockchain,and the …
Z Wang, Q Hu - arXiv preprint arXiv:2110.02182, 2021 - arxiv.org
… First, we investigate how blockchain can be applied to federallearning from the perspective … law-quality data and maliciousbehaviours. • Public blockchain in BCFL generally requires …
… maliciousbehaviors. The results in this work not only pose a new research direction in federatedlearning, but … In this work, we define maliciousbehaviors as actions that intentionally …
… However, if the maliciousbehavior happens when the value of reputation is higher than h, the reputation drops by 1, so does the reward in the subsequent global epoch. …
… However, the behavioral trust of beacon nodes is affected when there are … This paper proposes a blockchain based mechanism for malicious node detection in the IoSTs. The …
YE Oktian, B Stanley, SG Lee - Symmetry, 2022 - mdpi.com
… Our evaluations show that the proposed solutions made federatedlearning more reliable. … higher rewards while punishing maliciousbehaviors. Hence, running federatedlearning in an …
Y Qi, MS Hossain, J Nie, X Li - Future Generation Computer Systems, 2021 - Elsevier
… If a delegate executes maliciousbehaviors during the consensus process, the deposit will be confiscated and the delegate is also put on a blacklist and removed from the delegate …