SavedAdd your journal

Journals / Harran Üniversitesi Mühendislik Dergisi / 2026 / Cilt: 11 Sayı: 2

Cyber Threat Detection from QR Code Images via Topological Data Analysis and Machine Learning: A Novel Approach

Topolojik Veri Analizi ve Makine Öğrenmesiyle QR Kod Görsellerinden Siber Tehditlerin Tespiti: Yenilikçi Bir Yaklaşım

Hilal Nur Çetin0009-0000-9736-5441
Birkan Büyükarıkan(ISPARTA UYGULAMALI BİLİMLER ÜNİVERSİTESİ)0000-0002-9703-9678
Pages
108–121
Publication Date
2026-06-30
🏛️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)

The findings demonstrate that topological features extracted from QR code representations offer strong representational capabilities for cyber threat classification and that the proposed approach constitutes a viable alternative in cybersecurity.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study presents an innovative approach that combines topological data analysis (TDA) with machine learning algorithms to classify cyber threat data encoded as QR codes.
📊
Key Findings & Data:The tabular data were first converted into Quick Response (QR) code images, which were then resized to 32×32 and 64×64 pixel dimensions. cubical complex representations were generated from the resulting QR code images, and topological features corresponding to the H0 and H1 dimensions were extracted using the persistent homology method.
💡
Conclusion & Impact:The findings demonstrate that topological features extracted from QR code representations offer strong representational capabilities for cyber threat classification and that the proposed approach constitutes a viable alternative in cybersecurity.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Siber tehdit · QR kod · Topolojik veri analizi

Abstract

This study presents an innovative approach that combines topological data analysis (TDA) with machine learning algorithms to classify cyber threat data encoded as QR codes. This study used a tabular dataset containing metadata on network traffic. The tabular data were first converted into Quick Response (QR) code images, which were then resized to 32×32 and 64×64 pixel dimensions. cubical complex representations were generated from the resulting QR code images, and topological features corresponding to the H0 and H1 dimensions were extracted using the persistent homology method. These features were converted into fixed-dimensional vectors via the Persistence Image (PI) transformation and analyzed at different PI resolution levels (10×10, 20×20, 40×40, and 60×60). The feature vectors were evaluated using the eXtreme Gradient Boosting, Light Gradient Boosting Machine, CatBoost, AdaBoost, and Gradient Boosting (GB) algorithms, with 5-fold cross-validation. According to experimental results, the proposed TDA-AdaBoost model achieved an accuracy score of 99.16% with a 32×32 pixel QR dataset and a resolution of 20×20 PI. Furthermore, the TDA-GB model achieved an accuracy score of 95.10% with a 64×64 pixel QR dataset and a resolution of 10×10 PI. The findings demonstrate that topological features extracted from QR code representations offer strong representational capabilities for cyber threat classification and that the proposed approach constitutes a viable alternative in cybersecurity.

Özet

Bu çalışma, QR koda dönüştürülmüş siber tehdit verilerinin sınıflandırılmasında topolojik veri analizi (TDA) ile makine öğrenmesi algoritmalarını birleştiren yenilikçi bir yaklaşım sunmaktadır. Çalışmada, ağ trafiğine ilişkin meta verileri içeren tablosal bir veri seti kullanılmıştır. Tablosal veriler, öncelikle Quick Response (QR) kod görsellerine dönüştürülmüş ve ardından bu görseller 32×32 ve 64×64 piksel boyutlarına ölçeklendirilmiştir. Elde edilen QR kod görüntüleri üzerinden kübik kompleks temsilleri oluşturulmuş ve kalıcı homoloji yöntemi kullanılarak H0 ve H1 boyutlarına ait topolojik özellikler çıkarılmıştır. Bu özellikler, kalıcılık görüntüsü (PI) dönüşümü ile sabit boyutlu vektörlere dönüştürülmüş ve farklı PI çözünürlük seviyelerinde (10×10, 20×20, 40×40 ve 60×60) analiz edilmiştir. Elde edilen özellik vektörleri, eXtreme Gradient Boosting, Light Gradient Boosting Machine, CatBoost, AdaBoost ve Gradient Boosting (GB) algoritmaları ile 5 katlı çapraz doğrulama yöntemiyle değerlendirilmiştir. Deneysel sonuçlara göre, 32×32 piksel boyutundaki QR veri seti ve 20×20 PI çözünürlük seviyesinde önerilen TDA-AdaBoost modeli %99,16 doğruluk değerine ulaşmıştır. Ayrıca, 64×64 piksel boyutundaki QR veri seti ve 10×10 PI çözünürlük seviyesinde TDA-GB modeli ile %95,10 doğruluk değeri elde edilmiştir. Bulgular, QR kod temsillerinden çıkarılan topolojik özelliklerin siber tehdit sınıflandırmasında güçlü bir temsil kabiliyeti sunduğunu ve önerilen yaklaşımın siber güvenlik alanında uygulanabilir bir alternatif oluşturduğunu göstermektedir.

🔖

Cite This Article

Çetin, H. N., Büyükarıkan, B. (2026). Cyber Threat Detection from QR Code Images via Topological Data Analysis and Machine Learning: A Novel Approach. Harran Üniversitesi Mühendislik Dergisi, Cilt: 11 Sayı: 2, 108–121. https://doi.org/10.46578/humder.1838535

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (45)

  1. Yu S., & Carroll F. (2022). Implications of AI in national security: understanding the security issues and ethical challenges. In: Artificial intelligence in cyber security: Impact and implications: Security challenges, technical and ethical issues, forensic investigative challenges. Montasari, R., & Jahankhani, H. (Eds), Springer, pp 157–175.
  2. Li Y., & Liu Q. (2021). A comprehensive review study of cyber-attacks and cyber security; Emerging trends and recent developments. Energy Reports, 7: 8176–8186.
  3. Okoli U. I., Obi O. C., Adewusi A. O., & Abrahams T. O. (2024). Machine learning in cybersecurity: A review of threat detection and defense mechanisms. World Journal of Advanced Research and Reviews, 21 (1): 2286–2295.
  4. Farooq H. M., & Otaibi N. M. (2018). Optimal machine learning algorithms for cyber threat detection. 2018 UKSim-AMSS 20th International Conference on Computer Modelling and Simulation (UKSim), 32–37.
  5. Boutaba R., Salahuddin M. A., Limam N., Ayoubi S., Shahriar N., Estrada-Solano F., & Caicedo O. M. (2018). A comprehensive survey on machine learning for networking: evolution, applications and research opportunities. Journal of Internet Services and Applications, 9 (1): 1–99.
  6. Kaur R., Gabrijelčič D., & Klobučar T. (2023). Artificial intelligence for cybersecurity: Literature review and future research directions. Information Fusion, 97: 101804.
  7. Toğaçar M. (2023). Kötü Amaçlı Yazılım Türlerinin Tespitinde Kullanılan 1B Verilerin 2B Barkod Türlerine Dönüştürülerek Derin Ağlarla Analizlerinin Gerçekleştirilmesi. Mühendislik Bilimleri ve Araştırmaları Dergisi, 5 (1): 169–177.
  8. Alaca Y., & Çelik Y. (2023). Cyber attack detection with QR code images using lightweight deep learning models. Computers & Security, 126: 103065.
  9. Trad F., & Chehab A. (2025). Detecting Quishing Attacks with Machine Learning Techniques Through QR Code Analysis. arXiv preprint arXiv:250503451.
  10. Sarkhi M., & Mishra S. (2024). Detection of QR code-based cyberattacks using a lightweight Deep Learning model. Engineering, Technology & Applied Science Research, 14 (4): 15209–15216.
  11. Khadilkar A., & Stamp M. (2025). Image-Based Malware Classification Using QR and Aztec Codes. In: Machine Learning, Deep Learning and AI for Cybersecurity. Stamp, M., & Jureček, M. (Eds), Springer, pp 3–35.
  12. Zhu Y., Brettin T., Xia F., Partin A., Shukla M., Yoo H., Evrard Y. A., Doroshow J. H., & Stevens R. L. (2021). Converting tabular data into images for deep learning with convolutional neural networks. Scientific reports, 11 (1): 11325.
  13. Edelsbrunner H., & Harer J. (2010). Computational topology: an introduction, American Mathematical Soc.
  14. Peng Y., Wang H., Sonka M., & Chen D. Z. (2024). PHG-Net: Persistent homology guided medical image classification. 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 7583–7592.
  15. Lima M. D. P., Giraldi G. A., & Junior G. F. M. (2023). Image Classification using Combination of Topological Features and Neural Networks. arXiv preprint arXiv:231106375.
  16. Chazal F., & Michel B. (2021). An introduction to topological data analysis: fundamental and practical aspects for data scientists. Frontiers in artificial intelligence, 4: 667963.
  17. Adams H., Emerson T., Kirby M., Neville R., Peterson C., Shipman P., Chepushtanova S., Hanson E., Motta F., & Ziegelmeier L. (2017). Persistence images: A stable vector representation of persistent homology. Journal of Machine Learning Research, 18 (8): 1–35.
  18. Zomorodian A., & Carlsson G. (2004). Computing persistent homology. The twentieth annual symposium on Computational geometry, 347–356.
  19. Ver Hoef L., Adams H., King E. J., & Ebert-Uphoff I. (2023). A primer on topological data analysis to support image analysis tasks in environmental science. Artificial Intelligence for the Earth Systems, 2 (1).
  20. Singh Y., Farrelly C. M., Hathaway Q. A., Leiner T., Jagtap J., Carlsson G. E., & Erickson B. J. (2023). Topological data analysis in medical imaging: current state of the art. Insights into Imaging, 14 (1): 58.
  21. Lee D., Lee S.-H., & Jung J.-H. (2023). The effects of topological features on convolutional neural networks—an explanatory analysis via GradCAM. Machine Learning: Science and Technology, 4 (3): 035019.
  22. Jassim S. A. (2020). Persistent homology features and multiple topologies for image analysis. Mobile Multimedia/Image Processing, Security, and Applications 2020, 113990A.
  23. Davies T. (2022). Topological data analysis for anomaly detection in host-based logs. arXiv preprint arXiv:220412919.
  24. Postol M., Diaz C., Simon R., & Wicke D. (2019). Time-series data analysis for classification of noisy and incomplete internet-of-things datasets. 2019 18th IEEE international conference on machine learning and applications (ICMLA), 1543–1550.
  25. Collins J., Iorga M., Cousin D., & Chapman D. (2020). Passive encrypted iot device fingerprinting with persistent homology. 34th Conference on Neural Information Processing Systems (NeurIPS 2020), 1-6.
  26. Adams H., & Moy M. (2021). Topology applied to machine learning: From global to local. Frontiers in Artificial Intelligence, 4: 668302.
  27. Reininghaus J., Huber S., Bauer U., & Kwitt R. (2015). A stable multi-scale kernel for topological machine learning. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4741–4748.
  28. Carriere M., Cuturi M., & Oudot S. (2017). Sliced Wasserstein kernel for persistence diagrams. 34th International Conference on Machine Learning, 70: 664–673.
  29. Afzaal H. (2024). Cyber Threat Detection. Kaggle. https://www.kaggle.com/datasets/hussainsheikh03/cyber-threat-detection.
  30. Glenn S., Cisewski-Kehe J., Zhu J., & Bement W. M. (2025). Tracking Temporal Evolution of Topological Features in Image Data. arXiv preprint arXiv:250817530.
  31. Singh Y., & Quaia E. (2025). Unraveling the Invisible: Topological Data Analysis as the New Frontier in Radiology’s Diagnostic Arsenal. Tomography, 11 (1): 6.
  32. Hatcher A. (2005). Algebraic topology, Cambridge: Cambridge Univ. Press.
  33. Zia A., Khamis A., Nichols J., Tayab U. B., Hayder Z., Rolland V., Stone E., & Petersson L. (2024). Topological deep learning: a review of an emerging paradigm. Artificial Intelligence Review, 57 (4): 77.
  34. Su Z., Liu X., Hamdan L. B., Maroulas V., Wu J., Carlsson G., & Wei G.-W. (2026). Topological data analysis and topological deep learning beyond persistent homology: a review. Artificial Intelligence Review, 59.
  35. Choe S., & Ramanna S. (2022). Cubical homology-based machine learning: An application in image classification. Axioms, 11 (3): 112.
  36. Alenizy H. A., & Berri J. (2025). Transforming tabular data into images via enhanced spatial relationships for CNN processing. Scientific Reports, 15 (1): 17004.
  37. Choe S. (2021). Cubical homology-based Image Classification-A Comparative Study, University of Winnipeg. Canada.
  38. Chen T., & Guestrin C. (2016). Xgboost: A scalable tree boosting system. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794.
  39. Ke G., Meng Q., Finley T., Wang T., Chen W., Ma W., Ye Q., & Liu T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. 31st International Conference on Neural Information Processing Systems, 3149-3157.
  40. Namburu A., Selvaraj P., & Varsha M. (2024). Product pricing solutions using hybrid machine learning algorithm. Innovations in Systems and Software Engineering, 20, 413-424
  41. Xia Y., He L., Li Y., Liu N., & Ding Y. (2020). Predicting loan default in peer-to-peer lending using narrative data. Journal of Forecasting, 39 (2): 260–280.
  42. Freund Y., & Schapire R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences, 55 (1): 119–139.
  43. Hastie T., Rosset S., Zhu J., & Zou H. (2009). Multi-class adaboost. Statistics and its Interface, 2 (3): 349–360.
  44. Selvapandian A., & Manivannan K. (2018). Performance analysis of meningioma brain tumor classifications based on gradient boosting classifier. International Journal of Imaging Systems and Technology, 28 (4): 295–301.
  45. Keskin S., & Sevli O. (2024). Machine learning based classification for spam detection. Sakarya University Journal of Science, 28 (2): 270–282.