Abstract

Even with powerful tools to detect and prevent phishing attacks, the threat remains one of the most prevalent cybersecurity issues. Although cybersecurity tools increasingly integrate artificial intelligence (AI) and machine learning (ML), one area remains persistently exploited by cybercriminals: human behavior, targeted through social engineering. This study analyzes the role of human behavior in phishing attacks from a behavioral cybersecurity perspective, combining a conceptual, literature-based synthesis with an empirical evaluation of five machine learning classifiers on two public phishing datasets comprising 69,700 labeled instances in total. The key behavioral dimensions analyzed are trust, perceived urgency, fear, curiosity, digital literacy, cybersecurity awareness, and decision-making biases. In the empirical evaluation, the Random Forest classifier achieved 97.11% and 95.58% accuracy on the two datasets, confirming the maturity of technical detection. A complementary scenario analysis restricted to deception cues that are, in principle, visible to end users retained approximately 91% accuracy on both datasets, indicating that the information required to recognize most phishing attacks is present in what users can observe, and that victimization arises primarily from cognitive and emotional manipulation rather than from an absence of information. The results indicate that technological solutions alone are insufficient in the absence of human-centered cybersecurity strategies and regular behavioral interventions. By integrating recent findings with quantitative evidence, the study advances the field of behavioral cybersecurity and presents a case for adaptive behavioral approaches to minimize phishing risks.

References

• Asiri, S., Xiao, Y., Alzahrani, S., Li, S., and Li, T. 2023. A survey of intelligent detection designs of HTML URL phishing attacks. IEEE Access 11, 6421–6443. DOI: https://doi.org/10.1109/ACCESS.2023.3237798
• Kapan, S. and Sora Gunal, E. 2023. Improved phishing attack detection with machine learning: a comprehensive evaluation of classifiers and features. Applied Sciences 13, 24, 13269. DOI: https://doi.org/10.3390/app132413269
• Carroll, F., Adejobi, J. A., and Montasari, R. 2022. How good are we at detecting a phishing attack? Investigating the evolving phishing attack email and why it continues to successfully deceive society. SN Computer Science 3, 2, 170. DOI: https://doi.org/10.1007/s42979-022-01069-1
• Baltuttis, D., Teubner, T., and Adam, M. T. P. 2024. A typology of cybersecurity behavior among knowledge workers. Computers and Security 140, 103741. DOI: https://doi.org/10.1016/j.cose.2024.103741
• Siponen, M., Topalli, V., Soliman, W., and Vestman, T. 2025. Reconsidering neutralization techniques in behavioral cybersecurity as a form of cybersecurity hygiene discounting. Computers and Security 150, 104306. DOI: https://doi.org/10.1016/j.cose.2024.104306
• Khan, N. F., Ikram, N., Murtaza, H., and Javed, M. 2023. Evaluating protection motivation based cybersecurity awareness training on Kirkpatrick's model. Computers and Security 125, 103049. DOI: https://doi.org/10.1016/j.cose.2022.103049
• Gahletia, K. 2025. Cybersecurity awareness in the age of social media: a behavioral study. International Journal for Research in Applied Science and Engineering Technology 13, 7, 46–49. DOI: https://doi.org/10.22214/ijraset.2025.72931
• Alyami, M., Alhotaylah, R., Alshehri, S., and Alghamdi, A. 2023. Phishing attacks on cryptocurrency investors in the Arab states of the Gulf. Journal of Risk and Financial Management 16, 5, 271. DOI: https://doi.org/10.3390/jrfm16050271
• Mosa, D. T., Shams, M. Y., Abohany, A. A., El-Kenawy, E. S. M., and Thabet, M. 2023. Machine learning techniques for detecting phishing URL attacks. Computers, Materials and Continua 75, 1, 1271–1290. DOI: https://doi.org/10.32604/cmc.2023.036422
• Shukla, S., Misra, M., and Varshney, G. 2024. HTTP header-based phishing attack detection using machine learning. Transactions on Emerging Telecommunications Technologies 35, 1, e4872. DOI: https://doi.org/10.1002/ett.4872
• Alsariera, Y. A., Alanazi, M. H., Said, Y., and Allan, F. 2024. An investigation of AI-based ensemble methods for the detection of phishing attacks. Engineering, Technology and Applied Science Research 14, 3, 14266–14274. DOI: https://doi.org/10.48084/etasr.7267
• Asiri, S., Xiao, Y., and Li, T. 2024. PhishTransformer: a novel approach to detect phishing attacks using URL collection and transformer. Electronics 13, 1, 30. DOI: https://doi.org/10.3390/electronics13010030
• Mersinas, K., Bada, M., and Furnell, S. 2025. Cybersecurity behavior change: a conceptualization of ethical principles for behavioral interventions. Computers and Security 148, 104025. DOI: https://doi.org/10.1016/j.cose.2024.104025
• Prümmer, J., van Steen, T., and van den Berg, B. 2024. A systematic review of current cybersecurity training methods. Computers and Security 136, 103585. DOI: https://doi.org/10.1016/j.cose.2023.103585
• Jungebloud, T., Nguyen, N. H., Kim, D. D., and Zimmermann, A. 2025. Model-based structural and behavioral cybersecurity risk assessment in system designs. Computers and Security 157, 104543. DOI: https://doi.org/10.1016/j.cose.2025.104543
• Joshi, C., Slapničar, S., Yang, J., and Ko, R. K. L. 2025. Contrasting the optimal resource allocation to cybersecurity controls and cyber insurance using prospect theory versus expected utility theory. Computers and Security 154, 104450. DOI: https://doi.org/10.1016/j.cose.2025.104450
• Tin, T. T., Xin, K. J., Aitizaz, A., Tiung, L. K., Keat, T. C., and Sarwar, H. 2023. Machine learning-based predictive modeling of cybersecurity threats utilizing behavioral data. International Journal of Advanced Computer Science and Applications 14, 9, 832–840. DOI: https://doi.org/10.14569/IJACSA.2023.0140987
• Al-Sabbagh, A., Hamze, K., Khan, S., and Elkhodr, M. 2024. An enhanced K-means clustering algorithm for phishing attack detections. Electronics 13, 18, 3677. DOI: https://doi.org/10.3390/electronics13183677
• Alamri, E. K., Alnajim, A. M., and Alsuhibany, S. A. 2022. Investigation of using CAPTCHA keystroke dynamics to enhance the prevention of phishing attacks. Future Internet 14, 3, 82. DOI: https://doi.org/10.3390/fi14030082
• Almeida, F. 2025. Comparative analysis of EU-based cybersecurity skills frameworks. Computers and Security 151, 104329. DOI: https://doi.org/10.1016/j.cose.2025.104329
• Mohammad, R. M., Thabtah, F., and McCluskey, L. 2012. An assessment of features related to phishing websites using an automated technique. In Proceedings of the International Conference for Internet Technology and Secured Transactions (ICITST 2012). IEEE, 492–497.
• Vrbančič, G., Fister, I., Jr., and Podgorelec, V. 2020. Datasets for phishing websites detection. Data in Brief 33, 106438. DOI: https://doi.org/10.1016/j.dib.2020.106438.
• Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. 2011. Scikit-learn: machine learning in Python. Journal of Machine Learning Research 12, 2825–2830.