Authors : Sudhesh Kumar; Dr. Minni Sinha

Volume/Issue : Volume 10 - 2025, Issue 8 - August

---

Google Scholar : https://tinyurl.com/3j2fbfn7

Scribd : https://tinyurl.com/3rsxmnbb

DOI : https://doi.org/10.38124/ijisrt/25aug925

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

Note : Google Scholar may take 30 to 40 days to display the article.

---

Abstract : The proliferation of cyberattacks in modern digital ecosystems poses significant challenges for businesses, governments, and individuals alike. Traditional reactive security measures have proven insufficient in countering sophisticated and evolving cyber threats. This research proposes an AI-driven predictive model to identify and prevent cyber threats before they materialize. By analyzing patterns of cybercrime incidents and leveraging advanced machine learning algorithms, we present a proactive security architecture capable of enhancing early threat detection. Experimental results demonstrate the model’s efficiency in terms of accuracy, precision, recall, and F1-score, indicating its viability as an industry solution.

Keywords : Cybersecurity, Cyber Threat Prediction, Machine Learning, Artificial Intelligence, Threat Intelligence, Pattern Analysis.

References :

1. J. Smith, “AI in Cybersecurity: A Predictive Approach,” IEEE Trans. Inf. Forensics, vol. 16, pp. 1024–1036, 2021.
2. L. Nguyen, “Deep Learning for Intrusion Detection,” Comput. Security J., vol. 48, pp. 99–115, 2021.
3. R. Shah, “Ensemble Models in Threat Detection,” Int. J. Cyber Sci., vol. 12, no. 3, pp. 212–230, 2022.
4. A. Gomez, “Reinforcement Learning for Cyber Defense,” IEEE Access, vol. 9, pp. 12211–12224, 2023.
5. NIST, “AI in Enterprise Security,” NIST Cybersecurity Framework, 2024.
6. M. Patel, “Zero-Day Attack Detection Techniques,” J. Inf. Security Res., vol. 8, no. 4, pp. 333–345, 2022.
7. K. Li, “Big Data Analytics in Cybersecurity,” IEEE Cloud Comput., vol. 10, pp. 41–55, 2021.
8. V. Singh, “Hybrid Models for Threat Analysis,” ACM Comput. Surveys, vol. 55, no. 6, pp. 1–29, 2022.
9. P. Brown, “Machine Learning in SOC Automation,” Cyber Defense Rev., vol. 9, pp. 75–89, 2023.
10. Y. Zhao, “Blockchain for Secure Cyber Infrastructure,” Future Gen. Comput. Syst., vol. 124, pp. 377–390, 2022.
11. H. Tan, “Pattern Recognition in Cybersecurity,” Int. Conf. on InfoSec, pp. 43–50, 2021.
12. A. Kumar, “Threat Prediction Using Neural Networks,” Springer AI J., vol. 37, pp. 220–233, 2023.
13. F. Rossi, “Data Imbalance Solutions in Cybersecurity,” IEEE Trans. Neural Netw., vol. 34, pp. 89–101, 2024.
14. G. Lopez, “Real-Time Cyber Monitoring,” J. Cybersecurity Eng., vol. 6, no. 1, pp. 56–70, 2023.
15. R. Ahmed, “IoT Security and Predictive Analytics,” Sensors J., vol. 23, pp. 1455–1468, 2023.
16. S. Choi, “AI in Cloud Security,” IEEE Cloud Comput., vol. 11, pp. 90–102, 2024.
17. T. Evans, “Adversarial ML in Cybersecurity,” IEEE Sec. Privacy, vol. 22, pp. 35–48, 2023.
18. Z. Huang, “Cyber Threat Forecasting Techniques,” J. Inf. Tech., vol. 67, no. 2, pp. 178–192, 2022. [19] D. Mehta, “Advanced Feature Engineering for Threat Detection,” ACM Trans. Cybersecurity, vol. 8, pp. 111–126, 2024.
19. K. Roy, “Hybrid AI for Proactive Cyber Defense,” IEEE Access, vol. 12, pp. 3456–3470, 2025.
20. Sharafaldin, I., Lashkari, A.H., & Ghorbani, A.A. (2018). Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization. CICIDS 2017.
21. Kaggle. (2025). Network Intrusion Dataset (CIC-IDS-2017). https://www.kaggle.com/datasets/chethuhn/network-intrusion-dataset
22. DarkOwl. (2025). Darknet Intelligence Feeds. https://www.darkowl.com
23. FalconFeeds. (2025). Cyber Threat Intelligence Feeds. https://falconfeeds.io
24. Anomali. (2025). Threat Intelligence Marketplace. https://www.anomali.com/marketplace/threat-intelligence-feeds