EUVIMEDEUVIMED entdecken
Crossref

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

Hilal Nur Çetin, Birkan Büyükarıkan

Harran Üniversitesi Mühendislik Dergisi · 30.06.2026 · 11 (2) · 108-121

DOI: 10.46578/humder.1838535 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Harran Üniversitesi Mühendislik Dergisi, online erschienen am 30.06.2026. Verfasst von Hilal Nur Çetin und 1 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

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, 11(2), 108-121. https://doi.org/10.46578/humder.1838535

Vancouver

Çetin HN, Büyükarıkan B. Cyber Threat Detection from QR Code Images via Topological Data Analysis and Machine Learning: A Novel Approach. Harran Üniversitesi Mühendislik Dergisi. 2026;11(2):108-121. doi:10.46578/humder.1838535

BibTeX
@article{etin2026,
  author = {Çetin, Hilal Nur and Büyükarıkan, Birkan},
  title = {Cyber Threat Detection from QR Code Images via Topological Data Analysis and Machine Learning: A Novel Approach},
  journal = {Harran Üniversitesi Mühendislik Dergisi},
  year = {2026},
  volume = {11},
  number = {2},
  pages = {108--121},
  doi = {10.46578/humder.1838535}
}
Kostenlos starten →