Author Guidelines

Publications

Editorial

About

Archive Issue – Vol.5, Issue.4 (Oct-Dec 2025)

Archive Issue – Vol.5, Issue.4 (October-December 2025)


DDQN-BASED ADAPTIVE LIGHTWEIGHT HONEYPOT FRAMEWORK FOR INTELLIGENT CYBER THREAT DETECTION IN SMALL AND MEDIUM ENTERPRISES

Arshit Rawat, Devansh Namdev, Aditya Sharma, Anant Pratap Singh Sachan and Shivank Kumar Soni

Research Paper | Journal Paper

Vol.5, Issue.4, pp.1-07, Dep-2025

DOI: 10.5281/zenodo.17802728

Abstract References Citation Download

Abstract

Honeypots serve as deceptive cybersecurity systems that attract and engage attackers, providing valuable insights into their methods within controlled environments. However, traditional honeypots are largely static and passive, making them easily identifiable and ineffective against modern, adaptive cyber threats. Existing adaptive models offer incremental improvements but remain limited by predefined rules or simplified learning mechanisms, restricting their responsiveness to complex and evolving attacks. This paper introduces an RL-Enhanced Adaptive Honeypot that integrates a Dueling Double Deep Q-Network (DDQN)-based decision engine to enable autonomous behavioural adaptation. The system dynamically adjusts its defence posture by analysing attacker activity and environmental metrics represented in a structured state model. Through continuous learning and policy optimization, the honeypot transitions between observation, deception, and mitigation strategies, maintaining an average accuracy of approximately 96% across behavioural prediction and threat intelligence classification tasks. Future work aims to employ simulated multi-stage attack environments to pre-train reinforcement learning agents, fostering the development of self-evolving honeypots capable of real-time, intelligent cyber defence.

Key-Words / Index Term: Adaptive Cyber Defence, DDQN, Honeypot, Network Security, Reinforcement Learning.

References

      1. A. Alahmari and B. Duncan, "Cybersecurity Risk Management in Small and Medium-Sized Enterprises: A Systematic Review of Recent Evidence," 2020 International Conference on Cyber Situational Awareness, Data Analytics and Assessment (CyberSA), Dublin, Ireland, 2020, pp. 1-5, 10.1109/CyberSA49311.2020.9139638
      2. Z. Aradi and A. Bánáti, "The Role of Honeypots in Modern Cybersecurity Strategies," 2025 IEEE 23rd World Symposium on Applied Machine Intelligence and Informatics (SAMI), Stará Lesná, Slovakia, 2025, pp. 000189-000196, 10.1109/SAMI63904.2025.10883300
      3. T. T. Nguyen and V. J. Reddi, "Deep Reinforcement Learning for Cyber Security," in IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 8, pp. 3779-3795, Aug. 2023, 10.1109/TNNLS.2021.3121870.
      4. Van Hasselt, Hado, Arthur Guez, and David Silver. "Deep reinforcement learning with double q-learning." Proceedings of the AAAI conference on artificial intelligence. Vol. 30. No. 1. 2016. https://doi.org/10.1609/aaai.v30i1.10295
      5. P. Holgado, V. A. Villagrá and L. Vázquez, "Real-Time Multistep Attack Prediction Based on Hidden Markov Models," in IEEE Transactions on Dependable and Secure Computing, vol. 17, no. 1, pp. 134-147, 1 Jan.-Feb. 2020, 10.1109/TDSC.2017.2751478.
      6. Pashaei, Abbasgholi, et al. "Early Intrusion Detection System using honeypot for industrial control networks." Results in Engineering 16 (2022): 100576. https://doi.org/10.1016/j.rineng.2022.100576
      7. B. Hu and J. Li, "Shifting Deep Reinforcement Learning Algorithm Toward Training Directly in Transient Real-World Environment: A Case Study in Powertrain Control," in IEEE Transactions on Industrial Informatics, vol. 17, no. 12, pp. 8198-8206, Dec. 2021, 10.1109/TII.2021.3063489.
      8. Caminero, Guillermo, Manuel Lopez-Martin, and Belen Carro. "Adversarial environment reinforcement learning algorithm for intrusion detection." Computer Networks 159 (2019): 96-109. https://doi.org/10.1016/j.comnet.2019.05.013
      9. Y. Liu, H. Wang, M. Peng, J. Guan, J. Xu and Y. Wang, "DeePGA: A Privacy-Preserving Data Aggregation Game in Crowdsensing via Deep Reinforcement Learning," in IEEE Internet of Things Journal, vol. 7, no. 5, pp. 4113-4127, May 2020, 10.1109/JIOT.2019.2957400
      10. Q. Xu, Z. Su and R. Lu, "Game Theory and Reinforcement Learning Based Secure Edge Caching in Mobile Social Networks," in IEEE Transactions on Information Forensics and Security, vol. 15, pp. 3415-3429, 2020, 10.1109/TIFS.2020.2980823.
      11. Sethi, K., Sai Rupesh, E., Kumar, R. et al. A context-aware robust intrusion detection system: a reinforcement learning-based approach. Int. J. Inf. Secur. 19, 657–678 (2020). https://doi.org/10.1007/s10207-019-00482-7
      12. S. Otoum, B. Kantarci and H. Mouftah, "Empowering Reinforcement Learning on Big Sensed Data for Intrusion Detection," ICC 2019 - 2019 IEEE International Conference on Communications (ICC), Shanghai, China, 2019, pp. 1-7, 10.1109/ICC.2019.8761575
      13. Pacheco, Yulexis, and Weiqing Sun. "Adversarial Machine Learning: A Comparative Study on Contemporary Intrusion Detection Datasets." ICISSP.2021. https://www.scitepress.org/PublishedPapers/2021/102535/102535.pdf
      14. E. Suwannalai and C. Polprasert, "Network Intrusion Detection Systems Using Adversarial Reinforcement Learning with Deep Q-network," 2020 18th International Conference on ICT and Knowledge Engineering (ICT&KE), Bangkok, Thailand, 2020, pp. 1-7, 10.1109/ICTKE50349.2020.9289884
      15. Veluchamy, Selvakumar, and Ruba Soundar Kathavarayan. "Deep reinforcement learning for building honeypots against runtime DoS attack." International Journal of Intelligent Systems 37.7 (2022): 3981-4007. https://doi.org/10.1002/int.22708

Citation

Arshit Rawat, Devansh Namdev, Aditya Sharma, Anant Pratap Singh Sachan and Shivank Kumar Soni, "DDQN-BASED ADAPTIVE LIGHTWEIGHT HONEYPOT FRAMEWORK FOR INTELLIGENT CYBER THREAT DETECTION IN SMALL AND MEDIUM ENTERPRISES" International Journal of Scientific Research in Technology & Management, Vol.5, Issue.4, pp.1-07, 2025. DOI: 10.5281/zenodo.17802728

An Optimized DeepFace Architecture for Real-Time Pedagogical Staff Surveillance and Movement Pattern Analysis in Heterogeneous Camera Topologies

Nikhil Kushwaha, Mayur Bansal, Pradyumna Tripathi and Shivank Kumar Soni

Research Paper | Journal Paper

Vol.5, Issue.4, pp.08-14, Dep-2025

DOI: 10.5281/zenodo.17862281

Abstract References Citation Download

Abstract

To keep the workplace safe, accountable, and running smoothly, it's important to verify staff presence and follow their movements in a dynamic environment and changing conditions. However, traditional attendance and surveillance systems—often rely on manual validation or RFID-based tracking remain static, error-prone, and incapable of adapting to heterogeneous camera networks or various environmental conditions. Preexisting computer vision approaches offer limited scalability and struggle with real-time multi-camera synchronization which reduces accuracy and responsiveness in critical applications. This paper introduces a smart staff monitoring system that uses Optimized DeepFace–OpenCV–based surveillance framework that autonomously detects, verifies, and records staff presence across distributed IP camera feeds. The proposed system integrates facial embedding extraction, automated timetable mapping, and absence alert system to notify supervisors when assigned personnel are not detected within a set-time duration. A dual-interface Flask-based portal offers separate access modes for employees and supervisors, enabling attendance history, and absence alerts, live location visibility without compromising the privacy of the staff. Tests with different camera setups showed that the system is highly reliable, correctly recognizing faces nearly 97.8% (using SQLite) with a mean response latency of 1.3 seconds per frame even with changing lighting or movement scenarios. Looking forward, the farmwork aims to expand in the future toward edge-enabled analytics and IoT-integrated workforce management, fostering scalable deployment across educational, corporate, and industrial domains.

Key-Words / Index Term: DeepFace, OpenCV, Real-Time Surveillance, Staff Monitoring, Facial Recognition, Smart Automation, IP Camera Networks.

References

      1. Y. Taigman, M. Yang, M. Ranzato and L. Wolf, "DeepFace: Closing the Gap to Human-Level Performance in Face Verification," 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014, pp. 1701-1708, doi: 10.1109/CVPR.2014.220.
      2. F. Schroff, D. Kalenichenko and J. Philbin, "FaceNet: A unified embedding for face recognition and clustering," 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 815-823, doi: 10.1109/CVPR.2015.7298682.
      3. Dakhil, Nasreen & Abdulazeez, Adnan. (2024). Face Recognition Based on Deep Learning: A Comprehensive Review. Indonesian Journal of Computer Science. 13. DOI:10.33022/ijcs.v13i3.4037.
      4. G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller, “Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments,” Univ. Massachusetts, Amherst, Tech. Rep. 07-49, 2007. DOI: 10.48550/arXiv.1708.08197
      5. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov and L.-C. Chen, "MobileNetV2: Inverted Residuals and Linear Bottlenecks," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 4510-4520, doi: 10.1109/CVPR.2018.00474.
      6. P. Viola and M. Jones, "Rapid object detection using a boosted cascade of simple features," Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, Kauai, HI, USA, 2001, pp. I-I, doi: 10.1109/CVPR.2001.990517.
      7. Z. Cao, G. Hidalgo, T. Simon, S.-E. Wei and Y. Sheikh, "OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 1, pp. 172-186, Jan. 2021, doi: 10.1109/TPAMI.2019.2929257.
      8. OpenCV Documentation, “VideoCapture and Real-Time Processing,” Available: https://docs.opencv.org/. [Accessed: Jan. 2025].
      9. S. Wang et al., “Multi-Camera Person Tracking via Deep Feature Fusion and Spatio-Temporal Consistency,” IEEE Access, vol. 8, pp. 12489–12500, 2020.
      10. A. Hermans, L. Beyer, and B. Leibe, “In Defense of the Triplet Loss for Person Re-Identification,” arXiv:1703.07737, 2017. DOI: https://doi.org/10.48550/arXiv.1703.07737
      11. M. L. Tran and T. T. Nguyen, “A Real-Time Face Recognition Attendance System Using Deep Learning,” International Journal of Advanced Computer Science and Applications, vol. 11, no. 9, 2020.
      12. A. Khan, R. Ahmad, and S. Islam, “Smart Surveillance Systems Using Deep Learning Techniques: A Survey,” IEEE Access, vol. 9, pp. 17307–17337, 2021.
      13. J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” arXiv:1804.02767, 2018. DOI: https://doi.org/10.48550/arXiv.1804.02767
      14. A. Dosovitskiy et al., “An Image is Worth 16×16 Words: Transformers for Image Recognition at Scale,” Proc. ICLR, 2021.
      15. Flask Documentation, “Flask — Lightweight WSGI Web Application Framework,” Available: https://flask.palletsprojects.com/. [Accessed: Jan. 2025].
      16. SQLite Documentation, “SQLite Features and Architecture,” Available: https://www.sqlite.org/. [Accessed: Jan. 2025].
      17. A. R. Chowdhury, H. J. Choi, and J. Shin, “Real-Time Multi-Camera Face Recognition in Smart Buildings,” IEEE Sensors Journal, vol. 20, no. 18, pp. 10856–10865, 2020.
      18. S. Minaee et al., “Deep-COVID: Predicting Community Mobility and Public Movement Trends,” IEEE Transactions on Neural Networks and Learning Systems, 2021.
      19. A. Ruiz, O. Revaud, J. Verbeek, and H. Jégou, “Learning Compact Face Representations for Identity Recognition,” Proc. IEEE CVPR, 2017.
      20. C. Szegedy et al., “Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning,” Proc. AAAI, 2017. DOI: https://doi.org/10.1609/aaai.v31i1.11231
      21. Halder, R., Chatterjee, R., Sanyal, D.K., Mallick, P.K. (2020). Deep Learning-Based Smart Attendance Monitoring System. In: Mandal, J., Mukhopadhyay, S. (eds) Proceedings of the Global AI Congress 2019. Advances in Intelligent Systems and Computing, vol 1112. Springer, Singapore. https://doi.org/10.1007/978-981-15-2188-1_9
      22. J.K. Aggarwal and M.S. Ryoo. 2011. Human activity analysis: A review. ACM Comput. Surv. 43, 3, Article 16 (April 2011), 43 pages. https://doi.org/10.1145/1922649.1922653

Citation

Nikhil Kushwaha, Mayur Bansal, Pradyumna Tripathi and Shivank Kumar Soni, "An Optimized DeepFace Architecture for Real-Time Pedagogical Staff Surveillance and Movement Pattern Analysis in Heterogeneous Camera Topologies" International Journal of Scientific Research in Technology & Management, Vol.5, Issue.4, pp.08-14, 2025. DOI: 10.5281/zenodo.17862281