Conference
Open access
2026
Federated Learning for Malware Image Classification under Data Heterogeneity
This paper presents an empirical study of federated MIC under varying degrees of data heterogeneity across three popular malware image datasets, and proposes an entropy-aware client selection strategy that filters candidate client sub-sets based on class entropy and shows that this strategy outperforms standard random...
Victor Taiwo, Cemal Nisan, M. Athallah et al.
· International Conference on... · 0 citations