EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A lightweight system call intrusion detection method for resource-constrained embedded platforms

Xueting Bai, Jian Zhao, Yinzhang Cheng, Dongdong Yang, Zhenyu Lu, Zhihong Zheng

it - Information Technology · 05.11.2026

DOI: 10.1515/itit-2026-0048 ↗

Kurz gefasst

Fachartikel in der Zeitschrift it - Information Technology, online erschienen am 05.11.2026. Verfasst von Xueting Bai und 5 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

System-call-based intrusion detection on resource-constrained embedded platforms must balance detection accuracy, deployment overhead, and online integration. This paper proposes a lightweight host-based intrusion detection method that combines a CNN-Transformer model, multidimensional robustness optimization, progressive model compression, and online detection on embedded hosts. Two one-dimensional convolution layers extract local system-call patterns, a Transformer encoder captures long-range dependencies, and attention pooling aggregates salient evidence for trajectory-level classification. Under a trajectory-level data-splitting protocol, controlled experiments are conducted on data augmentation, R-Drop regularization, attention/pooling mechanisms, and auxiliary objectives. A progressive compression pipeline is then applied, including architecture exploration, graph-wide channel masking with gradient-constrained fine-tuning, physical channel removal, and module-wise post-training quantization (PTQ). Experiments on the Australian Defence Force Academy Linux Dataset (ADFA-LD) show that the combined model achieves F1 scores of 0.941 ± 0.013 and 0.869 ± 0.021 on the balanced and imbalanced test sets, respectively, with false positive rates (FPRs) of 0.085 ± 0.048 and 0.026 ± 0.009. After physical channel removal at d = 28, the parameter count and floating-point operations (FLOPs) decrease to 60.76 k and 108.13 M, respectively. Partial module-wise PTQ further reduces the model size to 304.36 KB. An ARM64 prototype based on Quick Emulator (QEMU), the Linux audit daemon (auditd), Job-Tree aggregation, and sliding-window inference validates the end-to-end pipeline for system-call collection, inference, alerting, and data upload.

Zitieren

APA

Bai, X., Zhao, J., Cheng, Y., Yang, D., Lu, Z., & Zheng, Z. (2026). A lightweight system call intrusion detection method for resource-constrained embedded platforms. it - Information Technology. https://doi.org/10.1515/itit-2026-0048

Vancouver

Bai X, Zhao J, Cheng Y, Yang D, Lu Z, Zheng Z. A lightweight system call intrusion detection method for resource-constrained embedded platforms. it - Information Technology. 2026. doi:10.1515/itit-2026-0048

BibTeX
@article{Bai2026,
  author = {Bai, Xueting and Zhao, Jian and Cheng, Yinzhang and Yang, Dongdong and Lu, Zhenyu and Zheng, Zhihong},
  title = {A lightweight system call intrusion detection method for resource-constrained embedded platforms},
  journal = {it - Information Technology},
  year = {2026},
  doi = {10.1515/itit-2026-0048}
}
Kostenlos starten →