AI-powered framework for real-time dark web monitoring and cybersecurity threat detection

Sharma, Amit Kumar; Babbar, Nandini; Pal, Prajeeta; Verma, Neeraj Kumar; Saini, Ravindra Kumar

doi:10.47974/JDMSC-2440

Open Access Research Article

AI-powered framework for real-time dark web monitoring and cybersecurity threat detection

Amit Kumar Sharmaamit.sharma@jaipur.manipal.eduDepartment of Computer and Communication Engineering Manipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile → , ^*Nandini BabbarCorresponding authornandini.babbar@jaipur.manipal.eduDepartment of IoT and Intelligent Systems Manipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile → , Prajeeta Palprajeeta.219303115@muj.manipal.eduDepartment of Computer and Communication Engineering Manipal University Jaipur Jaipur, Rajasthan, 303007, IndiaView full profile → , Neeraj Kumar Vermaneeraj.verma@jaipur.manipal.eduDepartment of Data Science Manipal University JaipurDepartment of Data Science and Engineering Manipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile → , Ravindra Kumar Sainiravindra.saini@jaipur.manipal.eduDepartment of Information Technology Manipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile →

* Corresponding author · click or hover a name for details

pp. 2955–2966Vol. 28Issue 8December 2025DOI: 10.47974/JDMSC-2440 Crossmark XML

Received:: 08 Jan 2025
Published Online:: 08 Dec 2025
Article type:: Research Article
Language:: EN
Article no.:: JDMSC-2440
Pages:: 2955–2966

Abstract

The dark web dating back from the 1970s encompasses an unknown part of the internet that has an abstract and protected layer. Its uses range from the illegal breaching of internet security and drug trafficking to ransomware attacks. Tracking threat actor’s activities is impossible because of the dark webs’ decentralized infrastructure, with anonymity networks such as TOR and I2P. To counter this issue, deep learning methods like convolutional neural networks (CNNs), recurrent neural networks (RNNs) also called Long Short-Term Memory (LSTM) networks, and transformers (e.g. BERT) have been proposed in this research with the aim of developing a dark web security enhancement system. These models deal with challenges of encryption, anonymity, multilingualism, actively changing threats, and among others as encryption-deficient algorithms with content categorization, harmful activity detection, and anomalous behavior forecasting. The system has shown to reach 93.13% accuracy which proves that the proposed model is beneficial for proactive engagement in cybersecurity systems as real-time threat detection is achieved with minimal false alarms. Lastly, the paper contributes to the discussion of ethical challenges regarding privacy and artificial intelligence misuse by outlining reasonable measures to combat cybercrime and protect user rights.

Keywords

Dark web Security Deep learning Machine learning Threat detection Natural language processing CNN RNN Anomaly detection AI monitoring

Subject Classifications

94A6068M2568T0568T50

References

[1] A. P. Singh and M. Singh, “MS real-time malware detection in encrypted network traffic using machine learning with time-based features,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 26, pp. 841–850 (2023).
[2] S. Nazah, S. Huda, J. Abawajy, and M. M. Hassan, “Evolution of dark web threat analysis and detection: A systematic approach,” IEEE Access, vol. 8, pp. 171796–171819 (2020).
[3] C. A. Murty, H. Rana, R. Verma, R. Pathak, and P. H. Rughani, “Building an AI/ML-based classification framework for dark web text data,” in Proc. Int. Conf. on Computing and Communication Networks (ICCCN 2021), Singapore: Springer Nature Singapore, pp. 93–111 (2022).
[4] I. Bibi, A. Akhunzada, and N. Kumar, “Deep AI-powered cyber threat analysis in IIoT,” IEEE Internet of Things Journal, vol. 10, no. 9, pp. 7749–7760 (2022).
[5] N. Sun, M. Ding, J. Jiang, W. Xu, X. Mo, Y. Tai, and J. Zhang, “Cyber threat intelligence mining for proactive cybersecurity defense: A survey and new perspectives,” IEEE Communications Surveys & Tutorials, vol. 25, no. 3, pp. 1748–1774 (2023).
[6] A. Jøsang, “AI and cybersecurity,” in Cybersecurity: Technology and Governance, Cham: Springer Nature Switzerland, pp. 321–335 (2024).
[7] V. Adewopo, B. Gonen, N. Elsayed, M. Ozer, and Z. S. Elsayed, “Deep learning algorithm for threat detection in hackers forum (deep web),” arXiv preprint arXiv:2202.01448 (2022).
[8] S. K. Sharma and A. Kumar, “A cellular automata approach for extending data privacy and security of edge computing,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 27, no. 2-B, pp. 601–612 (2024), doi: 10.47974/JDMSC-1894.
[9] S. Arvind, B. Unhelkar, S. S. Shankar, P. Chakrabarti, and S. V. Devika, “Advancing cyber threat detection through deep learning in management information systems,” Journal of Management Information Systems, vol. 27, no. 8, pp. 2409–2417 (2024).
[10] A. Fayzi, M. Fayzi, and K. D. Ahmadi, “Dark web activity classification using deep learning,” arXiv preprint arXiv:2306.07980 (2023).
[11] J. Saleem, R. Islam, and M. A. Kabir, “The anonymity of the dark web: A survey,” IEEE Access, vol. 10, pp. 33628–33660 (2022).
[12] I. H. Sarker, “Deep cybersecurity: A comprehensive overview from neural network and deep learning perspective,” SN Computer Science, vol. 2, no. 3, p. 154 (2021).
[13] V. M. Ngo, S. McKeever, and C. Thorpe, “Identifying online child sexual texts in dark web through machine learning and deep learning algorithms,” in APWG.EU Technical Summit and Researchers Sync-Up (APWG.EU-Tech 2023), CEUR Workshop Proceedings, vol. 3631, pp. 1–6 (2023), doi: 10.21427/wfn5-rt72.
[14] P. Singh, M. Kumar, N. Sharma, P. Kumar, and Shweta, “Study of cyber threat intelligence, risk management and methods,” Journal of Information and Optimization Sciences, vol. 46, no. 1, pp. 65–74 (2025), doi: 10.47974/JIOS-1852.
[15] J. Saini, “LSTM based deep learning approach to detect online violent activities over dark web,” Multimedia Tools and Applications, vol. 82 (2023), doi: 10.1007/s11042-023-17222-8.

Views: 93Downloads: 10Citations: 1