Quantization-Aware Federated Learning for Resource-Constrained IoT Intrusion Detection: Accuracy, Communication and Robustness Trade-Offs
Future Internet · 18.11.2026 · 18 (11) · 638
DOI: 10.3390/fi18110638 ↗Kurz gefasst
Fachartikel in der Zeitschrift Future Internet, online erschienen am 18.11.2026. Verfasst von Rubini Pandu und 5 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Federated learning (FL) allows Internet of Things (IoT) gateways to train a shared intrusion detection system (IDS) without exporting raw network traffic, yet three constraints govern whether it is practical at the network edge: the memory and compute budget of the device, the capacity of the uplink, and exposure to poisoned updates from compromised clients. Existing studies largely address these constraints one at a time. This paper presents a systematic study of quantization-aware federated learning (QAFL) for IoT intrusion detection that jointly varies the on-device weight precision (32, 8 and 4 bits), the uplink update precision (32, 8, 4 and 2 bits, with and without error feedback), the server aggregation rule and the degree of statistical heterogeneity across clients. We also examine fixed-range update quantization, in which a server-declared quantization range bounds the influence of any single client as a side effect of compression. Across 876 training runs on three public benchmarks (CICIoT2023, Edge-IIoTset and TON_IoT) under Dirichlet non-IID partitioning, 8-bit weights with 4-bit updates retain 99.7% of full-precision macro-F1 (58.81 versus 58.98) while reducing per-round uplink traffic by 8×, model memory by 3.6× and estimated inference energy by 4.8×, and post-training quantization proves as effective as quantization-aware training for these compact models. Two-bit stochastic updates match full-precision accuracy with 15.9× less uplink traffic, but only without error feedback, which reduced 2-bit macro-F1 by 5.5 points; diagnostic runs trace this loss mainly to error-feedback memories that grow to 9 to 18 times the size of the update, with stale memories under partial participation adding to it. Fixed-range quantization reduced the macro-F1 loss caused by 20% sign-flipping clients from 59.1 to 3.8 points with plain FedAvg, at no cost in clean accuracy. A control with full-precision coordinate clipping at the same threshold gives the same protection, so the benefit comes from the server-set range rather than from the quantization grid. The defense bounds the magnitude but not the direction of malicious updates: a worst-case attacker that stays within the range attains this bound and defeats plain FedAvg from 20% to 25% attackers, and the distance-from-median filter of the closest prior framework is more robust whenever the server can inspect individual updates. Fixed-range quantization is thus a zero-cost, format-enforced bound that complements robust aggregation rather than replacing it. We consolidate these results into configuration guidelines for resource-constrained IoT deployments. All experiments run on a single commodity cloud GPU.
Zitieren
APA
Pandu, R., Munirathnam, L., Muralidhar, M., Babu, D. R. K., Ilagure, Z., & Yogarayan, S. (2026). Quantization-Aware Federated Learning for Resource-Constrained IoT Intrusion Detection: Accuracy, Communication and Robustness Trade-Offs. Future Internet, 18(11), 638. https://doi.org/10.3390/fi18110638
Vancouver
Pandu R, Munirathnam L, Muralidhar M, Babu DRK, Ilagure Z, Yogarayan S. Quantization-Aware Federated Learning for Resource-Constrained IoT Intrusion Detection: Accuracy, Communication and Robustness Trade-Offs. Future Internet. 2026;18(11):638. doi:10.3390/fi18110638
BibTeX
@article{Pandu2026,
author = {Pandu, Rubini and Munirathnam, Lakshmi and Muralidhar, Mohan and Babu, Dirasavancha Raghunath Kumar and Ilagure, Zakea and Yogarayan, Sumendra},
title = {Quantization-Aware Federated Learning for Resource-Constrained IoT Intrusion Detection: Accuracy, Communication and Robustness Trade-Offs},
journal = {Future Internet},
year = {2026},
volume = {18},
number = {11},
pages = {638},
doi = {10.3390/fi18110638}
}
EUVIMED