Research of the Capabilities of Deep Learning Algorithms to Protection Against Phishing Attacks

Sofia P. Korniukhina, Olga R. Laponina

Abstract


Phishing is one of the most common threats on the Internet which is why the development of effective protection methods is an extremely important task. This article discusses works that use the capabilities of machine and deep learning algorithms to protect against phishing attacks, as well as developed the comparison criteria and carried out the comparative analysis of solutions. The comparison of protection systems against phishing attacks was carried out according to the following criteria: the type of analyzed elements (HTML, URL, CSS); the dataset preprocessing methods (normalization and feature selection); the required sample size; the ML/DL algorithms used to detect phishing attacks; the number of errors of the 1st and 2nd kind, the quality criteria of the model. In the works CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory) are most frequently studied, both separately and in combination with each other. Also, the SVM (Support Vector Machine) and DT (Decision Tree) algorithms, which are used for classification problems, are often studied.

Full Text:

PDF (Russian)

References


The Open Web Application Security Project (OWASP) Top 10, https://owasp.org/Top10/#welcome-to-the-owasp-top-10-2021, 2021.

Mirjana Pejić Bach, Tanja Kamenjarska, Bersilav Žmuk Targets of phishing attacks: The bigger fish to fry // Procedia Computer Science. - 2022. - №204. - С. 448-455.

Butt, U.A., Amin, R., Aldabbas, H. et al. Cloud-based email phishing attack using machine and deep learning algorithm // Complex Intell. Syst. - 2022.

Yuan, X.: PhD Forum: Deep Learning-Based Real-Time Malware Detection with Multi-Stage Analysis. In 2017 IEEE International Conference on Smart Computing (SMARTCOMP), pp. 1–2 (2017)

Saxe, J., Berlin, K.: eXpose: A Character-Level Convolutional Neural Network with Embeddings For Detecting Malicious URLs, File Paths and Registry Keys (2017)

Shima, K., et al.: Classification of URL bitstreams using Bag of Bytes (2018)

Vazhayil, A., Vinayakumar, R., Soman, K.: Comparative Study of the Detection of Malicious URLs Using Shallow and Deep Networks. In 2018 9th International Conference on Computing, Communication and Networking Technologies (ICCCNT), pp. 1–6 (2018)

Zhang, X., Zeng, Y., Jin, X.-B., Yan, Z.-W., Geng, G.-G.: Boosting the phishing detection performance by semantic analysis. In 2017 IEEE International Conference on Big Data (BigData), pp. 1063–1070 (2017)

Vanhoenshoven, F., Napoles, G., Falcon, R., Vanhoof, K., Koppen, M.: Detecting malicious URLs using machine learning techniques. In 2016 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1–8 (2016)

Chen, W., Zhang, W., Su, Y.: Phishing Detection Research Based on LSTM Recurrent Neural Network, pp. 638–645. Springer, Singapore (2018)

Zhang, J., Li, X.: Phishing Detection Method Based on Borderline-Smote Deep Belief Network, pp. 45–53. Springer, Cham (2017)

Aksu, D., Turgut, Z., Üstebay, S., Aydin, M.A.: Phishing Analysis of Websites Using Classification Techniques, pp. 251–258. Springer, Singapore (2019)

Zhao, J., Wang, N., Ma, Q., Cheng, Z.: Classifying Malicious URLs Using Gated Recurrent Neural Networks, pp. 385–394. Springer, Cham (2019)

Jiang, J., et al.: A Deep Learning Based Online Malicious URL and DNS Detection Scheme, pp. 438–448. Springer, Cham (2018)

Spaulding, J., Mohaisen, A.: Defending Internet of Things Against Malicious Domain Names using D-FENS. In 2018 IEEE/ACM Symposium on Edge Computing (SEC), pp. 387–392 (2018)

Pereira, M., Coleman, S., Yu, B., DeCock, M., Nascimento, A.: Dictionary Extraction and Detection of Algorithmically Generated Domain Names in Passive DNS Traffic, pp. 295–314. Springer, Cham (2018)

Rao, R.S., Pais, A.R.: Detection of phishing websites using an efficient feature-based machine learning framework. Neural Comput. Appl., 1–23 (2018)

Sur, C.: DeepSeq: learning browsing log data based personalized security vulnerabilities and counter intelligent measures. J. Ambient Intell. Humaniz. Comput., 1–30 (2018)

Vrbanˇciˇc, G., Fister, I., Podgorelec, V.: Swarm Intelligence Approaches for Parameter Setting of Deep Learning Neural Network. In Proceedings of the 8th International Conference on Web Intelligence, Mining and Semantics—WIMS ’18, pp. 1–8 (2018)


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность MoNeTec 2024

ISSN: 2307-8162