Quantum-Assisted Client Selection for Federated Learning-based Intrusion Detection Systems via QAOA
Proceedings of the AAAI Symposium Series · 06.11.2026 · 10 (1) · 758-765
DOI: 10.1609/aaaiss.v10i1.43486 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 06.11.2026. Verfasst von Youssef Hadi und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Federated Learning (FL) is emerging as a distributed privacy-preserving paradigm, aiming to build a strong machine learning (ML) model in a distributed manner. Client selection in FL is a critical challenge for building intrusion detection systems, especially in heterogeneous Internet of Things (IoT) networks, where Non-Independent and Identically Distributed (Non-IID) data partitioning causes classical selection strategies to suffer from catastrophic forgetting of minority attack classes. This paper presents a Quantum Approximate Optimization Algorithm (QAOA) based framework that formulates client selection as a Quadratic Unconstrained Binary Optimization (QUBO) problem encoding client utility, communication latency, a cardinality constraint, and an optional group diversity term, solved at each communication round using the QAOA. To reduce quantum circuit width for near-term hardware compatibility, we investigate two qubit reduction strategies in this paper: hierarchical client clustering and classical pre-filtering. Extensive experiments on three IoT intrusion detection benchmarks under heterogeneous Non-IID distributions show that our proposed approach improves macro F1-score by up to 30% over Greedy-TopK selection and by up to 29% over random client selection. Our ablation studies confirm that the quantum-assisted selection advantage emerges specifically under Non-IID distributions. On the most challenging dataset, where two attack categories represent less than 0.5% of the data, the proposed method achieves superior results than other client selection methods on aggregate metrics while offering superior precision and convergence stability.
Zitieren
APA
Hadi, Y., Kadi, A., Moudoud, H., & Houda, Z. A. E. (2026). Quantum-Assisted Client Selection for Federated Learning-based Intrusion Detection Systems via QAOA. Proceedings of the AAAI Symposium Series, 10(1), 758-765. https://doi.org/10.1609/aaaiss.v10i1.43486
Vancouver
Hadi Y, Kadi A, Moudoud H, Houda ZAE. Quantum-Assisted Client Selection for Federated Learning-based Intrusion Detection Systems via QAOA. Proceedings of the AAAI Symposium Series. 2026;10(1):758-765. doi:10.1609/aaaiss.v10i1.43486
BibTeX
@article{Hadi2026,
author = {Hadi, Youssef and Kadi, Adam and Moudoud, Hajar and Houda, Zakaria Abou El},
title = {Quantum-Assisted Client Selection for Federated Learning-based Intrusion Detection Systems via QAOA},
journal = {Proceedings of the AAAI Symposium Series},
year = {2026},
volume = {10},
number = {1},
pages = {758--765},
doi = {10.1609/aaaiss.v10i1.43486}
}
EUVIMED