SavedAdd your journal

Journals / Bilişim Teknolojileri Dergisi / 2026 / Cilt: 19 Sayı: 1

Exploring Autoencoders for Anomaly Detection in Intrusion Detection Systems

Saldırı Tespit Sistemlerinde Anomali Tespiti için Otomatik Kodlayıcıların Araştırılması

Awab Khalefa(SAKARYA UNIVERSITY, FACULTY OF ARTS AND SCIENCES)0009-0004-2203-2481
Ahmet Zengin(SAKARYA UNIVERSITY, FACULTY OF ENGINEERING)0000-0003-0384-4148
Pages
53–62
Publication Date
2026-01-31
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Overall, the findings highlight the importance of threshold selection, dataset characteristics, and representation quality in anomaly-based intrusion detection.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This paper presents the development and evaluation of an Intrusion Detection System (IDS) based on a Denoising Autoencoder (DAE).
📊
Key Findings & Data:Three benchmark datasets—NSL-KDD, UNSW-NB15, and CTU-IoT—were used to assess the model’s capability to detect anomalous network behavior across diverse environments.
💡
Conclusion & Impact:Overall, the findings highlight the importance of threshold selection, dataset characteristics, and representation quality in anomaly-based intrusion detection.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:saldırı tespit sistemi (STS) · gürültü azaltan otomatik kodlayıcı (GAOK) · anomali tespiti

Abstract

This paper presents the development and evaluation of an Intrusion Detection System (IDS) based on a Denoising Autoencoder (DAE). Three benchmark datasets—NSL-KDD, UNSW-NB15, and CTU-IoT—were used to assess the model’s capability to detect anomalous network behavior across diverse environments. The proposed DAE achieved 86.1% accuracy and an 87.1% F1-Score on NSL-KDD, 94.8% accuracy on UNSW-NB15, and up to a 78.6% F1-Score on CTU-IoT depending on the anomaly threshold. These results are comparable to or exceed several autoencoder-based IDS approaches in the literature. Overall, the findings highlight the importance of threshold selection, dataset characteristics, and representation quality in anomaly-based intrusion detection.

Özet

Bu çalışma, Gürültü Giderici Özyinelemeli Kodlayıcı (Denoising Autoencoder, DAE) tabanlı bir Saldırı Tespit Sistemi (IDS) tasarımını ve değerlendirilmesini sunmaktadır. Modelin farklı saldırı türlerini normal ağ trafiğinden ayırt etme başarımını incelemek için NSL-KDD, UNSW-NB15 ve CTU-IoT veri setleri kullanılmıştır. Önerilen DAE, NSL- KDD veri setinde %86.1 doğruluk ve %87.1 F1-Skoru, UNSW-NB15 veri setinde %94.8 doğruluk ve CTU-IoT veri setinde eşik değerine bağlı olarak %78.6’ya kadar F1-Skoru elde etmiştir. Sonuçlar, literatürdeki birçok özyinelemeli- kodlayıcı tabanlı IDS çalışmasıyla karşılaştırılabilir veya daha yüksek performans sağlamaktadır. Genel olarak bulgular, eşik seçimi, veri seti özellikleri ve temsil öğrenme kalitesinin anomali tabanlı saldırı tespitinde kritik rol oynadığını göstermektedir.

🔖

Cite This Article

Khalefa, A., Zengin, A. (2026). Exploring Autoencoders for Anomaly Detection in Intrusion Detection Systems. Bilişim Teknolojileri Dergisi, Cilt: 19 Sayı: 1, 53–62. https://doi.org/10.17671/gazibtd.1746322

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (17)

  1. S. M. Kasongo, Y. Sun, "Performance Analysis of Intrusion Detection Systems Using a Feature Selection Method on the UNSW-NB15 Dataset", Journal of Big Data, 7, 105, 2020.
  2. M. S. Yadav, R. Kalpana, "Data Preprocessing for Intrusion Detection System Using Encoding and Normalization Approaches", 2019 11th International Conference on Advanced Computing (ICOAC), Chennai, India, 265-269, 18-20 Dec, 2019.
  3. F. Farahnakian, J. Heikkonen, "A deep auto-encoder-based approach for an intrusion detection system", 2018 20th International Conference on Advanced Communication Technology (ICACT), 2018.
  4. Y. Lin, et al., "GEE: A Gradient-based Explainable Variational Autoencoder for Network Anomaly Detection", arXiv:1903.06661, 2019.
  5. J. Kim, J. Kim, H. L. Kim, M. Kim, E. G. Kim, "Denoising Autoencoder with Dropout based Network Anomaly Detection", International Conference on Systems and Economic Engineering (ICSEA 2019), Valencia, Spain, 2019. A. A. Al-kadi, O. Al-kadi, "Analysis of Autoencoders for Network Intrusion Detection", Sensors, 21(13), 4294, 2021.
  6. S. Moraboena, G. Ketepalli, P. Ragam, "A Deep Learning Approach to Network Intrusion Detection Using Deep Autoencoder", Revue d'Intelligence Artificielle, 34(4), 457-463, 2020.
  7. C. Park, J. Lee, Y. Kim, J.-G. Park, H. Kim, D. Hong, "An Enhanced AI-Based Network Intrusion Detection System Using Generative Adversarial Networks", IEEE Internet of Things Journal, 10(3), 2330-2345, 2023.
  8. P. V. Ambiga, M. P. Ananthi, "A Review on Network Intrusion Detection", International Journal for Scientific Research and Development, 5(1), 2017.
  9. K. B. Kandasamy, et al., "Unsupervised Feature Extraction and Reconstruction Using Parameterized Quantum Circuits", arXiv:2502.07667, 2025.
  10. B. A. I. El-Aala, et al., "Enhanced Intrusion Detection in IIoT Networks: A Lightweight Approach with Autoencoder-Based Feature Learning", arXiv:2501.15266, 2025.
  11. A. Alkadi, N. Moustafa, B. Turnbull, K-K. R. Choo, "Analyzing Autoencoder-Based Intrusion Detection System Performance: Impact of Hidden Layers", Journal of Information Security and Cybercrimes Research, 5(2), 1-19, 2022.
  12. K. S. Park, S. Kim, J. Oh, J. Choi, "Graph Attention Auto-Encoders", arXiv:1905.10715, 2019.
  13. R. Daş, M. Z. Gündüz, "Analysis of Cyber-Attacks in IoT-based Critical Infrastructures", International Journal of Information Security Science, 8(4), 122-133, 2019.
  14. W. Wng, F. Harrou, B. Bouyeddou, S.-M. Senouci, Y. Sun, "Cyber-attacks detection in industrial systems using artificial intelligence-driven methods", International Journal of Critical Infrastructure Protection, 38, 100542, 2022.
  15. H. C. Altunay, Z. Albayrak, M. Çakmak, "Autoencoder-Based Intrusion Detection in Critical Infrastructures", Current Trends in Computing, 2(1), 1-12, 2024.
  16. H. S. Mavikumbure, C. S. Wickramasinghe, D. L. Marino, V. Cobilean, M. Manic, "Anomaly detection in critical-infrastructures using autoencoders: A survey", 2022 48th Annual Conference of the IEEE Industrial Electronics Society (IECON), 1-7, 2022.
  17. M. S. Al-Daweri, K. A. Z. Ariffin, S. Abdullah, M. F. E. M. Senan, "An Analysis of the KDD99 and UNSW-NB15 Datasets for the Intrusion Detection System", Symmetry, 12(10), 1666, 2020.