Authors : Rutuja Anant Pillai; Ankush Dhamal

Volume/Issue : Volume 10 - 2025, Issue 12 - December

---

Google Scholar : https://tinyurl.com/satu2r2v

Scribd : https://tinyurl.com/2ukc4ss6

DOI : https://doi.org/10.38124/ijisrt/25dec1341

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

---

Abstract : The growth of polymorphic malware and malicious URLs highlights the weaknesses of traditional signature-based and heuristic defenses, especially against zero-day threats. This research proposes an AI-driven detection framework that combines Python-based static feature extraction with OpenAI’s GPT-4.1-mini to classify threats using structured prompts, offering explanations and confidence scores. Based on the Cognitive Security framework, it shifts cybersecurity from reactive rules to adaptive, intelligence-driven protection. Initial conceptual results suggest better zero-day detection, fewer false positives, and clearer forensic insights, demonstrating the transformative potential of generative AI in cyber defense [1].

References :

1. World Economic Forum, “The Global Risks Report 2024,” 2024. [Online].
2. Al-Turaiki and N. Al-Twaijry, “A survey of malware detection techniques,” in 2016 8th International Conference on Information Technology (ICIT), pp. 200-205.
3. Jaffal, N. O., et al. (2025). “Large Language Models in Cybersecurity: A Survey of Applications and Challenges.” MDPI Cybersecurity.
4. Ferrag, M. A., et al. (2025). “Generative AI in cybersecurity: A comprehensive review of the future of cybersecurity through Generative AI and Large Language Models (LLMs).” ScienceDirect.
5. Motlagh, F. N., et al. (2025). “Large Language Models in Cybersecurity: State-of the-Art.” ScitePress.
6. Al Balawi, M. (2024). “Generative AI for Advanced Malware Detection.” IEEE Xplore.
7. Rashid, F., et al. (2025). “LLMs are one-shot URL classifiers and explainers.” ScienceDirect.
8. Kibriya, H., et al. (2025). “Lightweight malicious URL detection using deep learning and large language models.” Nature Scientific Reports.
9. Nasution, A. H., et al. (2025). “Benchmarking 21 Open-Source Large Language Models for Phishing Detection.” MDPI Information.
10. Ji, F., et al. (2025). “How Can We Effectively Use LLMs for Phishing Detection?”
11. Vinayakumar, R., et al. (2017). “Deep android malware detection and classification.” ICACCI.
12. Raff, E., et al. (2018). “Malware Detection by Eating a Whole EXE.” IEEE SPW.
13. Al-Dhaheri, A. S., et al. (2023). “Leveraging GPT-3 for Malware Behavior Description Generation.” IEEE Cyber Security.
14. Li, Z., et al. (2022). “Malicious URL Detection Based on BERT and Attention Mechanism.” IEEE CITS.
15. Bao, T., et al. (2025). “Generating Synthetic Malware Samples Using Generative AI.” SJSU ScholarWorks.
16. Morris, A. M. (2025). “Detecting Generative-AI-Enabled Polymorphic Malware.” ODU Digital Commons.
17. Bao, T., et al. (2024). “Generative AI-Based Effective Malware Detection for Embedded Computing Systems.” arXiv:2404.02344
18. Silva, J., & Westphall, C. B. (2024). “Large Language Models for Cyber Security: A Systematic Literature Review.” ACM DL.
19. Yigit, Y., et al. (2024). “When LLMs meet cybersecurity: A systematic literature review.” Springer.
20. Al-Mansoori, M. A., et al. (2024). “Chatphishdetector: Detecting phishing sites using large language models.” IEEE Xplore.
21. Gupta, S., et al. (2024). “A Review of Generative AI in Cybersecurity: Threats and Opportunities.” ResearchGate.
22. Kumar, A., et al. (2024). “Phishing Detection using LLMs: A Comparative Study.” IEEE.
23. Zhang, X., et al. (2024). “Zero-day Malware Detection with LLM-based Static Analysis.”
24. Smith, J., et al. (2024). “Cognitive Security: The Role of AI in Modern Cyber Defense.” Journal of Cybersecurity.
25. Brown, L., et al. (2024). “Explainable AI for Malware Classification: A Survey.” ScienceDirect.
26. D. S. Vinayakumar, R., Soman, K. P., & Poornachandran, P. (2017). “Deep android malware detection and classification,” in 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 1533- 1538.
27. E. C. D. C. Raff, J. Barker, J. Sylvester, R. Brandon, B. Catanzaro and C. Nicholas, “Malware Detection by Eating a Whole EXE,” 2018 IEEE Security and Privacy Workshops (SPW), San Francisco, CA, USA, 2018, pp. 250-257.
28. S. Al-Dhaheri, M. A. Al-Mansoori, and M. A. Al-Marzooqi, “Leveraging GPT-3 for Malware Behavior Description Generation,” in 2023 International Conference on Cyber Security and Protection of Digital Services (Cyber Security), pp. 1-6.
29. Z. Li, S. Chen, and Y. Liu, “Malicious URL Detection Based on BERT and Attention Mechanism,” in 2022 International Conference on Computer, Information and Telecommunication Systems (CITS), pp. 1-6.