An Energy-Efficient Intrusion Detection Offloading Based on DNN for Edge Computing

• João A. Simioni PUCPR https://orcid.org/0009-0002-7088-1758
• Eduardo K. Viegas PUCPR https://orcid.org/0000-0002-5050-6363
• Altair O. Santin PUCPR https://orcid.org/0000-0002-2341-2177

DOI: https://doi.org/10.5753/sbseg_estendido.2026.31770

Resumo

To address the computational limitations associated with implementing Deep Neural Network (DNN)–based intrusion detection on resource-constrained devices, this work proposes an energy-efficient edge architecture that integrates distributed early-exit DNN models to minimize processing overhead while preserving detection performance. Our approach employs multi-objective optimization to dynamically offload complex tasks to the cloud, thereby balancing the trade-off between accuracy and energy consumption under operator constraints. Furthermore, it incorporates a rejection mechanism and confidence calibration via temperature scaling to ensure reliability as network traffic evolves. Experiments on a 7TB year-long dataset demonstrate that the system reduces edge energy consumption to only 1% while offloading only 10% of events, all without compromising detection accuracy and even improving the F1-Score by 0.02 compared to traditional approaches.

Referências

Ahmad, Z., Khan, A. S., Shiang, C. W., Abdullah, J., and Ahmad, F. (2020). Network intrusion detection system: A systematic study of machine learning and deep learning approaches. Transactions on Emerging Telecommunications Technologies, 32(1).

Angelucci, S., Valentini, R., Levorato, M., Santucci, F., and Chiasserini, C. F. (2024). Edge computing with early exiting for adaptive inference in mobile autonomous systems. In ICC 2024 - IEEE International Conference on Communications, pages 2980–2985.

Colocrese, M., Koyuncu, E., and Seferoglu, H. (2024). Early-exit meets model-distributed inference at edge networks. In 2024 IEEE 30th International Symposium on Local and Metropolitan Area Networks (LANMAN), pages 39–44.

Espindola, A. d. S., Santin, A. O., Casimiro, A., Ferreira, P. M., and Viegas, E. K. (2026). Understanding the adversary: A survey of adversarial machine learning in network intrusion detection. Computer Science Review, 62:100995.

Fontugne, R., Borgnat, P., Abry, P., and Fukuda, K. (2010). MAWILab: Combining Diverse Anomaly Detectors for Automated Anomaly Labeling and Performance Benchmarking. In ACM CoNEXT ’10, Philadelphia, PA.

Hu, X., Chu, L., Pei, J., Liu, W., and Bian, J. (2021). Model complexity of deep learning: a survey. Knowledge and Information Systems, 63(10):2585–2619.

Moore, A. (2005). Discriminators for use in flow-based classification. In Dept. Comput. Sci., Univ. London, London, U.K., Rep. RR-05-13.

Simioni, J., Viegas, E. K., Santin, A., and Horchulhack, P. (2025). An early exit deep neural network for fast inference intrusion detection. In Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing, SAC ’25, page 730–737. ACM.

Teerapittayanon, S., McDanel, B., and Kung, H. (2016). BranchyNet: Fast inference via early exiting from deep neural networks. In 2016 23rd International Conference on Pattern Recognition (ICPR). IEEE.

Tekin, N., Acar, A., Aris, A., Uluagac, A. S., and Gungor, V. C. (2024). Energy consumption of on-device machine learning models for iot intrusion detection. Internet of Things, 21.

Wang, Y., Qin, G., Zou, M., Liang, Y., Wang, G., Wang, K., Feng, Y., and Zhang, Z. (2023). A lightweight intrusion detection system for internet of vehicles based on transfer learning and mobilenetv2 with hyper-parameter optimization. Multimedia Tools and Applications.