Open Access

ARTICLE

Quantized Intrusion Detection for Resource-Constrained IoT: A Comparative Evaluation of Efficiency and Adversarial Robustness

Saeed Ullah¹, Junsheng Wu^1,*, Mian Muhammad Kamal^2,*, Mohammed K. Alzaylaee³, Heba G. Mohamed^4,5

1 School of Software, Northwestern Polytechnical University, Xi’an, 710072, China
2 School of Electronic and Communication Engineering Quanzhou University of Information Engineering, Quanzhou, 362000, China
3 Department of Computing, College of Engineering and Computing in Al-Qunfudhah, Umm AL-Qura University, Makkah, Saudi Arabia
4 Department of Electrical Engineering, College of Engineering, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia
5 Electrical Department, College of Engineering, Alexandria Higher Institute of Engineering and Technology, Alexandria, 21421, Egypt

* Corresponding Authors: Junsheng Wu. Email: ; Mian Muhammad Kamal. Email:

Computers, Materials & Continua 2026, 88(3), 62 https://doi.org/10.32604/cmc.2026.084409

Received 22 April 2026; Accepted 04 June 2026; Issue published 23 July 2026

Abstract

The proliferation of Internet of Things (IoT) devices has introduced unprecedented security challenges, necessitating efficient intrusion detection systems (IDS) capable of operating under severe resource constraints. This research presents a hardware-informed empirical study of quantized neural-network-based intrusion detection for resource-constrained IoT platforms, using an ARM Cortex-M4 deployment target as a reference. We evaluate FP32, FP16, and INT8 TensorFlow Lite model variants derived from a lightweight 1D-CNN and assess their trade-offs in clean-data accuracy, model size, estimated inference latency, estimated energy consumption, and adversarial robustness. INT8-quantized model achieves 99.10% accuracy on clean data while maintaining 97.50% adversarial accuracy under Projected Gradient Descent (PGD) attacks with perturbation budget = 0.3. The quantized model achieves 12.0× latency reduction (0.083 vs. 0.995 ms) and 92.7% energy reduction (0.0083 vs. 0.1135 mJ) when compared to FP32. The memory footprint of the model is reduced by 55.7% from 58.02 to 25.72 KB. Our comprehensive analysis includes confusion matrices, ROC curves (AUC = 0.9964 for INT8), adversarial robustness heatmaps, and statistical significance testing via McNemar’s test. The results establish INT8 quantization as a viable solution for deploying robust IDS on resource-constrained IoT devices, achieving practical deployment feasibility without reducing detection performance.

---

Keywords

---