Authors : Ritaben M. Marwada; Nilesh Modi

Volume/Issue : Volume 11 - 2026, Issue 5 - May

Google Scholar : https://tinyurl.com/5cyymhyp

Scribd : https://tinyurl.com/5mxsnhd5

DOI : https://doi.org/10.38124/ijisrt/26May330

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Phishing and social engineering attacks have become more sophisticated, utilizing linguistic manipulation and contextual deception to bypass security measures that are traditionally fixed and rely on rule-based, signature matching, or large annotated datasets that fail when faced with rapidly changing threats. The current detection models have a hard time generalizing beyond known patterns, are still vulnerable to adversarial linguistic variations, and are heavily dependent on expensive and time-consuming data labelling. To overcome these issues, this study presents a generative NLP-driven framework that detects phishing linguistically and contextually by identifying persistent linguistic and contextual indicators of phishing behaviour through a generative AI model capable of creating realistic synthetic phishing samples, thus lessening the dependency on a large amount of labelled corpora. The method embodies a strong defense strategy that merges generalization-based learning with adversarial training to extend the resistance of the system against the ever-changing attack strategies and the presence of subtle manipulative cues. Moreover, the real-time alerting and feedback-driven adaptation loop provide a continuous system improvement and newly emerging threats' responsiveness. The anticipated results are the correct identification of already known and newly invented phishing attempts, the system's robustness against adversarial perturbations, better generalization over various threat scenarios, and the creation of a data-efficient process for generating synthetic samples. The entire investigation is geared towards producing a phishing detection system that is adaptive, resilient, and ready for deployment in the real world.

Keywords : Phishing Detection, Generative NLP, Social Engineering, Adversarial Training, Adaptive Cybersecurity.

References :

1. Akter, T. (2025). A Taxonomy and Multi-Layered Defense Framework for Generative AI-Powered Phishing.
2. Alauthman, M., Aldweesh, A., Al-Qerem, A., Alkasassbeh, M., Alateef, S., & Almomani, A. (2025). Synthetic Content Generation Impacts on Phishing and Impersonation Attacks Examining Cybersecurity Risks Produced by Generative AI (pp. 189-210): IGI Global Scientific Publishing.
3. Alsop, H., Maglaras, L., Janicke, H., Sarker, I. H., & Ferrag, M. A. (2025). Innovating Augmented Reality Security: Recent E2E Encryption Approaches. arXiv preprint arXiv:2509.10313.
4. Beydemir, A. B., Sezgin, U., Doğan, U., Aşıklar, B. E., Yerlikaya, F. A., & Bahtiyar, Ş. (2024). A Dynamically Selected GPT Model for Phishing Detection. Paper presented at the 2024 14th International Conference on Advanced Computer Information Technologies (ACIT).
5. Desolda, G., Greco, F., & Viganò, L. (2025). APOLLO: A GPT-based tool to detect phishing emails and generate explanations that warn users. Proceedings of the ACM on Human-Computer Interaction, 9(4), 1-33.
6. Gupta, S., Ray, R. K., Singh, A., & Kapoor, A. P. (2026). Building Adaptive Digital Immune Systems: A Framework for Large‐Scale Organizational Resilience. Digital Immune System: Principles and Practices, 305-321.
7. Jamal, S., Wimmer, H., & Sarker, I. H. (2024). An improved transformer‐based model for detecting phishing, spam and ham emails: A large language model approach. Security and Privacy, 7(5), e402.
8. Khan, H., Alam, M., Al-Kuwari, S., & Faheem, Y. (2021). Offensive AI: Unification of email generation through GPT-2 model with a game-theoretic approach for spear-phishing attacks. Paper presented at the IET Conference Proceedings CP786.
9. Koide, T., Fukushi, N., Nakano, H., & Chiba, D. (2024). Chatspamdetector: Leveraging large language models for effective phishing email detection. Paper presented at the International Conference on Security and Privacy in Communication Systems.
10. Koide, T., Nakano, H., & Chiba, D. (2024). Chatphishdetector: Detecting phishing sites using large language models. IEEE Access.
11. Ling, F., Yang, H., Xiao, Y., & Hu, L. (2024). Meta GPT-Based Agent for Enhanced Phishing Email Detection. Paper presented at the Proceedings of the 2024 14th International Conference on Communication and Network Security.
12. Masmoudi, S. (2025). Unveiling the human factor in cybercrime and cybersecurity: Motivations, behaviors, vulnerabilities, mitigation strategies, and research methods Cybercrime unveiled: Technologies for analysing legal complexity (pp. 41-91): Springer.
13. McIntosh, T. R., Susnjak, T., Arachchilage, N., Liu, T., Xu, D., Watters, P., & Halgamuge, M. N. (2025). Inadequacies of large language model benchmarks in the era of generative artificial intelligence. IEEE Transactions on Artificial Intelligence.
14. Merat, S., & Almuhtadi, W. (2025). Social Cyber Engineering and Advanced Security Algorithms: CRC Press.
15. Mohamed, N. (2025). Artificial intelligence and machine learning in cybersecurity: a deep dive into state-of-the-art techniques and future paradigms. Knowledge and Information Systems, 1-87.
16. Panda, S. P. (2025). The Evolution and Defense Against Social Engineering and Phishing Attacks. International Journal of Science and Research (IJSR).
17. Shibli, A. M., Pritom, M. M. A., & Gupta, M. (2024). Abusegpt: Abuse of generative ai chatbots to create smishing campaigns. Paper presented at the 2024 12th International Symposium on Digital Forensics and Security (ISDFS).
18. Tsinganos, N., Fouliras, P., & Mavridis, I. (2022). Applying BERT for early-stage recognition of persistence in chat-based social engineering attacks. Applied sciences, 12(23), 12353.
19. Tsinganos, N., Fouliras, P., & Mavridis, I. (2023). Leveraging dialogue state tracking for zero-shot chat-based social engineering attack recognition. Applied sciences, 13(8), 5110.
20. Tsinganos, N., Mavridis, I., & Gritzalis, D. (2022). Utilizing convolutional neural networks and word embeddings for early-stage recognition of persuasion in chat-based social engineering attacks. IEEE Access, 10, 108517-108529.
21. Verma, A., & Shri, C. (2025). Cyber security: A review of cyber crimes, security challenges and measures to control. Vision, 29(4), 478-492.
22. Zia, M. F., & Kalidass, S. H. (2024). Web Phishing Net (WPN): A scalable machine learning approach for real-time phishing campaign detection. Paper presented at the 2024 4th Intelligent Cybersecurity Conference (ICSC).