Journals / Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi / 2023 / Cilt: 28 Sayı: 2

Determination of Cyber Security Awareness Levels of Students with Machine Learning Methods

Öğrencilerin Siber Güvenlik Farkındalık Düzeylerinin Makine Öğrenmesi Yöntemleri ile Belirlenmesi

Pages
451–466
Publication Date
2023-08-31
DOI
—
🏛️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 most successful performance metrics were obtained with the Multi-Layer Perceptron algorithm with an accuracy of 0.98 and an F1 score of 0.96.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:With the rapid development of information and communication technologies, the number of devices using technology and the internet has increased and has entered all areas of life.
📊
Key Findings & Data:As a result of the tests performed, accuracy values ranging from 0.7-0.98 and F1 scores ranging from 0.7-0.96 has been obtained.
💡
Conclusion & Impact:The most successful performance metrics were obtained with the Multi-Layer Perceptron algorithm with an accuracy of 0.98 and an F1 score of 0.96.
🔬Design:Survey & Empirical Study
📍Scope:Comprehensive Sample
⚙️Variables:Makine öğrenmesi · Siber güvenlik · Siber güvenlik farkındalık düzeyi

Abstract

With the rapid development of information and communication technologies, the number of devices using technology and the internet has increased and has entered all areas of life. Developments in technology have brought the risk of users and devices encountering cyber threats. This work aims to determine students' cyber security awareness levels about cyber threats with machine learning methods. Therefore, data were collected from a sample population that was statistically representative of undergraduate students with the survey technique. The obtained data were analyzed by adopting the descriptive review model and the results of the analysis were presented in the study. Afterwards, the cyber security awareness levels of the students were determined by using the data set created from the survey data, Naive Bayes, Decision Tree, Random Forest, Nearest Neighbor, XGBoost, Gradient Boost, Support Vector Machines, Multi-Layer Perceptron algorithms. As a result of the tests performed, accuracy values ranging from 0.7-0.98 and F1 scores ranging from 0.7-0.96 has been obtained. The most successful performance metrics were obtained with the Multi-Layer Perceptron algorithm with an accuracy of 0.98 and an F1 score of 0.96.

Özet

Bilgi ve iletişim teknolojilerinin hızla gelişmesi ile birlikte teknoloji ve interneti kullanan cihaz sayısı artmış ve hayatın her alanına girmiştir. Teknolojideki gelişmeler kullanıcıların ve cihazların siber tehditlerle karşılaşma riskini de beraberinde getirmiştir. Bu çalışma; siber tehditlerle ilgili, öğrencilerin siber güvenlik farkındalık düzeylerini makine öğrenme yöntemleri ile tespit etmeyi amaçlamaktadır. Bu nedenle istatistiksel olarak lisans öğrencilerini temsil eden örnek bir kitleden anket tekniğiyle veri toplanmıştır. Elde edilen veriler, betimsel tarama modeli benimsenerek analiz edilmiş ve analiz sonuçları çalışmada ortaya konmuştur. Sonrasında anket verilerinden oluşturulan veri seti ile Naive Bayes, Karar Ağacı, Rastgele Orman, En Yakın Komşu, XGBoost, Gradient Boost, Destek Vektör Makineleri, Çok Katmanlı Algılayıcı algoritmaları kullanılarak öğrencilerin siber güvenlik farkındalık düzeylerinin tespiti yapılmıştır. Yapılan testler sonucunda 0.7-0.98 arasında değişen doğruluk değerleri, 0.7-0.96 arasında değişen F1 skorları elde edilmiştir. En başarılı performans metrikleri 0.98 doğruluk ve 0.96 F1-skoru ile Çok Katmanlı Algılayıcı algoritması ile elde edilmiştir.

🔖

Cite This Article

TOKMAK, M. (2023). Determination of Cyber Security Awareness Levels of Students with Machine Learning Methods. Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi, Cilt: 28 Sayı: 2, 451–466. https://ajindex.com/articles/959222

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (6)

  1. Abomhara, M., & Køien, G. M. (2015). Cyber Security and the Internet of Things: Vulnerabilities, Threats, Intruders and Attacks. Journal of Cyber Security and Mobility, 4(1), 65-88.
  2. Aldayel, M. S. (2012, December). K-Nearest Neighbor classification for glass identification problem. 2012 International Conference on Computer Systems and Industrial Informatics, Sharjah, United Arab Emirates. doi:10.1109/ICCSII.2012.6454522 Alzahrani, L. (2021). Statistical analysis of cybersecurity awareness issues in higher education institutes. International Journal of Advanced Computer Science and Applications, 12(11), 630-637. doi:10.14569/IJACSA.2021.0121172 Arpaci, I., & Sevinc, K. (2022). Development of the cybersecurity scale (CS-S): Evidence of validity and reliability. Information Development, 38(2), 218-226. doi:10.1177/0266666921997512 Balan, S., Gawand, S., & Purushu, P. (2018). Application of machine learning classification algorithm to cybersecurity awareness. Information Technology & Management Science (RTU Publishing House), 21, 45-48. doi:10.7250/itms-2018-0006
  3. Berrar, D. (2018). Bayes’ theorem and naive Bayes classifier. In S. Ranganathan, M. Gribskov, K. Nakai, & C. Schönbach (Eds.), Encyclopedia of Bioinformatics and Computational Biology: ABC of Bioinformatics (pp. 403-412).
  4. Amsterdam, The Netherlands: Elsevier Science Publisher. doi:10.1016/B978-0-12-809633-8.20473-1
  5. Breiman, L. (2001). Random forests. Machine learning, 45, 5-32. doi:10.1023/A:1010933404324 Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco California, USA. doi:10.1145/2939672.2939785 D’Silva, J. L., Samah, B. A., Shaffril, H. A. M., & Hassan, M. A. (2010). Factors that influence attitude towards ICT usage among rural community leaders in Malaysia. Australian Journal of Basic and Applied Sciences, 4(10), 5214-5220.
  6. Fraenkel, J. R., Wallen, N. E., & Hyun, H. (2012). How to design and evaluate research in education (C. 7). New York, USA: McGraw-hill Education. Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189-1232. doi:10.1214/aos/1013203451 Gibert, D., Mateu, C., & Planes, J. (2020). HYDRA: A multimodal deep learning framework for malware classification. Computers & Security, 95, 101873. doi:10.1016/j.cose.2020.101873 Gündüzalp, C. (2021). Üniversite çalışanlarının dijital veri