Efficient Anomaly Detection for Cyber-Physical Leveraging Knowledge Distillation and Model Quantization

Kamal Bella, Azidine Guezzaz (), Ravikumar Patchmuthu (), Said Benkirane, Mouaad Mohy-Eddine and Mourade Azrour
Additional contact information
Kamal Bella: Cadi Ayyad University, SISAR Team, LaRTiD Laboratory, Higher School of Technology
Azidine Guezzaz: Cadi Ayyad University, SISAR Team, LaRTiD Laboratory, Higher School of Technology
Ravikumar Patchmuthu: Universiti Teknology Brunei
Said Benkirane: Cadi Ayyad University, SISAR Team, LaRTiD Laboratory, Higher School of Technology
Mouaad Mohy-Eddine: Hassan II University, DELTA Lab, National School of Arts and Crafts
Mourade Azrour: Moulay Ismail University, Faculty of Sciences and Technics

A chapter in Reliability in Cyber-Physical Systems: The Human Factor Perspective, 2026, pp 105-117 from Springer

Abstract: Abstract Cyber-Physical Systems (CPS) are fundamental to modern technological advancement, they integrate physical and computational processes enabling real time interactions, and are often under constant security threats. Intrusion Detection Systems are essential in this context, they continuously monitor network traffic for anomalies that could indicate cyber-attacks. However, CPS are usually resource constrained environments and IDS can be computationally demanding, which makes real-time intrusion challenging. In this work, we address these limitations by providing a lightweight intrusion detection combining feature selection, knowledge distillation and quantization, aiming to drastically reduce the intrusion detection model size and inference time. In this setup, we experimented with 10, 20, 30 and 40 features from the NSL-KDD dataset, and developed a teacher model, a student model and a quantized model for each set of features. As a result, we found that the 30 features configuration set achieves the best balance between performance and efficiency, where the teacher model achieves 98.91% accuracy at 627 KB, the distilled model with 98.78% accuracy at 39.9 KB and finally, the quantized model achieves 98.80% accuracy at only 7.96 KB. These results showcase the abilities of combining these techniques in achieving low-cost intrusion detection without compromising performance.

Keywords: Intrusion detection; Cyber-physical systems; Knowledge distillation; Post-training quantization; Feature selection; Resource constraints (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:ssrchp:978-3-032-09917-4_7

Ordering information: This item can be ordered from
http://www.springer.com/9783032099174

DOI: 10.1007/978-3-032-09917-4_7

Access Statistics for this chapter

More chapters in Springer Series in Reliability Engineering from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().