AI-Based Cybersecurity Framework for Protecting Smart Surveillance Infrastructure in Mumbai

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 14 | 01 | Page :
    By

    Shweta Waghmare,

  • Sandeep Waghmare,

  1. Assistant Professor, Department of MCA, Thakur Institute of Management Studies, Career Development & Research Mumbai, Maharashtra, India
  2. Associate Systems Engineer, Department of MCA, Thakur Institute of Management Studies, Career Development & Research Mumbai, Maharashtra, India

Abstract

Smart city infrastructures increasingly rely on interconnected surveillance systems to ensure safety, operational efficiency, and public trust. However, the rapid expansion of IoT-based monitoring technologies has introduced new cyber risks, especially in high-density metropolitan areas. This paper proposes an AI-driven cyber resilience framework targeting smart surveillance infrastructure as a critical smart-living domain, focusing on Mumbai as a case study. Using the CIC-IDS2017 dataset, a machine learning-based intrusion detection model is developed to identify and classify cyber attacks affecting video surveillance networks. The framework integrates real- time anomaly detection, zero-trust access enforcement, and resilience assessment to strengthen security posture against advanced threats. The study highlights common attack vectors and vulnerabilities within smart city surveillance ecosystems and demonstrates improved detection accuracy in identifying malicious network activity. The findings emphasize the need for cybersecurity-aware governance and scalable AI solutions to protect national digital infrastructure.

Keywords: Smart City Security, Cyber Resilience, Artificial Intelligence, Smart Surveillance, Intrusion Detection, Machine Learning, Mumbai, CIC-IDS 2017

How to cite this article:
Shweta Waghmare, Sandeep Waghmare. AI-Based Cybersecurity Framework for Protecting Smart Surveillance Infrastructure in Mumbai. Journal Of Network security. 2026; 14(01):-.
How to cite this URL:
Shweta Waghmare, Sandeep Waghmare. AI-Based Cybersecurity Framework for Protecting Smart Surveillance Infrastructure in Mumbai. Journal Of Network security. 2026; 14(01):-. Available from: https://journals.stmjournals.com/jons/article=2026/view=241113


References

  1. Viksit Bharat 2047: Vision for a Developed Nation, accessed on Nov. 24, 2025. [Online]. Available: https://viksitindia.com/
  2. Press Information Bureau, “Transforming India with AI,” accessed on Nov. 24, 2025. [Online]. Available: https://www.pib.gov.in/PressReleasePage.aspx?PRID=2178092
  3. Ambimat Electronics, “Zero-Trust IoT Security for Smart Cities,” accessed on Nov. 24, 2025. [Online]. Available: https://ambimat.com/zero-trust-iot-security-for-smart-cities/
  4. Cybersecurity and Infrastructure Security Agency (CISA), “Cybersecurity Best Practices for Smart Cities,” 2023, accessed on            Nov.      24,       2025. [Online].       Available: https://www.cisa.gov/sites/default/files/2023-04/cybersecurity- best-practices-for-smart-cities_508.pdf
  5. ET Edge Insights, “The human firewall: India’s next frontier in digital security,” accessed on 24, 2025. [Online]. Available: https://etedge-insights.com/technology/cyber- security/the-human-firewall-indias-next-frontier-in-digital- security/
  6. World Economic Forum, “Building security into India’s digital public infrastructure,” accessed on Nov. 24, 2025. [Online]. Available: https://www.weforum.org/stories/2025/10/security-by-design- india-digital-public-infrastructure/
  7. ANI News, “Experts Convene in Delhi to Shape India’s Sustainable Urban Development Agenda,” accessed on Nov. 24, [Online].      Available: https://www.aninews.in/news/business/experts-convene-in-  delhi-to-shape-indias-sustainable-urban-development- agenda20251120133551
  8. Cogniteq, “Implementing Zero Trust Architecture in IoT Networks,” accessed on 24, 2025. [Online]. Available: https://www.cogniteq.com/blog/implementing-zero-trust- architecture-iot-networks
  9. MIDC, IT-ITES Policy 2015, accessed on Nov. 24, 2025. [Online]. Available: https://www.midcindia.org/wp- content/uploads/2021/09/IT-ITES_Policy_2015.pdf
  10. Cretum Advisory, “Maharashtra IT and ITES Policy,” accessed on Nov. 24, 2025. [Online]. Available: https://cretumadvisory.com/blog/maharashtra-it-and-ites-policy/
  11. InSec, “Securing India’s Smart Cities – Cybersecurity Challenges and Solutions,” accessed on 24, 2025. [Online]. Available: https://insec.in/cybersecurity-challenges-in-indias- smart-cities/
  12. Unit 42, Palo Alto Networks, “CVE-2021-28372: Vulnerability in Third-Party Technology Leaving IP Cameras and Surveillance Systems Vulnerable,” accessed on Nov. 24, 2025. [Online]. Available: https://unit42.paloaltonetworks.com/iot- supply-chain-cve-2021-28372/
  13. PwC India, “Creating cyber secure smart cities,” 2018, accessed on                    24,           2025.       [Online].  Available: https://www.pwc.in/assets/pdfs/publications/2018/creating- cyber-secure-smart-cities.pdf
  14. CyberPeace Foundation, “MHA Directs Stronger Cybersecurity in India’s Smart Cities,” accessed on 24, 2025. [Online].          Available: https://www.cyberpeace.org/resources/blogs/mha-directs- stronger-cybersecurity-in-indias-smart-cities
  15. “Reliability and Resilience of AI-Driven Critical Network Infrastructure Under Cyber-Physical Threats,” arXiv, accessed on 24,       2025.  [Online].  Available: https://arxiv.org/pdf/2510.19295
  16. “Deep Transfer Learning for Intrusion Detection in Industrial Control Networks: A Comprehensive Review,” arXiv, accessed on Nov. 24, 2025. [Online]. Available: https://arxiv.org/html/2304.10550v2
  17. University of New Brunswick, “Intrusion Detection Evaluation Dataset (CIC-IDS2017),” accessed on 24, 2025. [Online]. Available: https://www.unb.ca/cic/datasets/ids- 2017.html
  18. “A Framework for Cyber Threat Modeling and Risk Assessment in Smart City Environments,” Frontiers in Computer Science, accessed on Nov. 24, 2025. [Online]. Available: https://frontiersin.org/articles/10.3389/fcomp.2025.164717 9/full
  19. IEEE Xplore, “A Review of Intrusion Detection for IoT Using Machine Learning,” accessed on 24, 2025. [Online]. Available: https://ieeexplore.ieee.org/document/10803135
  20. IEEE Xplore, “A Systematic Review of Intrusion Detection Systems in IoT Using ML and DL,” accessed on 24, 2025. [Online].                                                                Available: https://ieeexplore.ieee.org/document/10099142
  21. IT Butler, “AI-Enhanced Network Monitoring: Real-Time Anomaly Detection Explained,” accessed on Nov. 24, 2025. [Online]. Available: https://itbutler.sa/blog/ai-enhanced- network-monitoring-real-time-anomaly-detection/
  22. PMC, “An IoT-Enabled Anomaly Detection System for Smart City Surveillance,” accessed on Nov. 24, 2025. [Online]. Available: https://pmc.ncbi.nlm.nih.gov/articles/PMC9966604/
  23. IEEE Xplore, “Intrusion Detection System (IDS) Classifications Using ML,” accessed on 24, 2025. [Online]. Available: https://ieeexplore.ieee.org/document/10730038/
  24. MDPI, “Ensemble Learning Framework for Anomaly Detection in Autonomous Driving Systems,” accessed on Nov. 24, 2025. [Online]. Available: https://www.mdpi.com/1424- 8220/25/16/5105
  25. IEEE Xplore, “Ensemble Learning Methods for Anomaly Intrusion Detection in Smart Grid,” accessed on Nov. 24, 2025. [Online]. Available: https://ieeexplore.ieee.org/document/9491891
  26. ResearchGate, “Integrating Machine Learning with Zero Trust Principles for Real-Time Threat Detection and Response,” accessed on                   24,     2025. [Online].       Available: https://www.researchgate.net/publication/395804705_Integratin g_Machine_Learning_with_Zero_Trust_Principles_for_Real- Time_Threat_Detection_and_Response_MUKUL_MANGLA
  27. Taylor & Francis Online, “Towards a Framework for Improving Cyber Security Resilience of Critical Infrastructure,” accessed on Nov. 24, 2025. [Online]. Available: https://www.tandfonline.com/doi/full/10.1080/12460125.2025.2 479546
  28. org, “AI-Driven Routing: Transforming Network Efficiency and Resilience,” accessed on Nov. 24, 2025. [Online]. Available: https://www.preprints.org/manuscript/202502.2005
  29. IEEE Xplore, “Securing Urban Landscape: Cybersecurity Mechanisms for Resilient Smart Cities,” accessed on Nov. 24, [Online]. Available: https://ieeexplore.ieee.org/iel8/6287639/10820123/10813375.pd  f
  30. IEEE Xplore, “Cyber Resilience in Smart Cities Using Bi- LSTM-Based Intrusion Detection System,” accessed on 24, 2025. [Online].       Available: https://ieeexplore.ieee.org/document/11033050
  31. PMC, “Evaluation of Machine Learning Techniques for Traffic Flow-Based Intrusion Detection,” accessed on Nov. 24, [Online].  Available: https://pmc.ncbi.nlm.nih.gov/articles/PMC9740321/
  32. SciTePress, “Network Intrusion Detection: A Comprehensive Analysis of CIC-IDS2017,” accessed on 24, 2025. [Online].           Available: https://www.scitepress.org/Papers/2022/107740/107740.pdf
  33. IEEE Xplore, “Machine Learning in Network Intrusion Detection: A Cross-Dataset Generalization Study,” accessed on 24,           2025.        [Online].             Available: https://ieeexplore.ieee.org/document/10704637
  34. ResearchGate, “Feature Selection Techniques for Efficient Intrusion Detection Using ML and DL,” accessed on Nov. 24, [Online]. Available: https://www.researchgate.net/publication/390746793_Feature_S election_Techniques_for_Efficient_Intrusion_Detection_Using_ Machine_Learning_and_Deep_Learning
  35. Sriwijaya University, “Important Features of CICIDS-2017 Dataset for Anomaly Detection,” accessed on Nov. 24, 2025. [Online]. Available: https://repository.unsri.ac.id/59517/1/Article-IJEEI- Important%20Features%20of%20CICIDS-2017%20Dataset.pdf
  36. ResearchGate, “Top 10 Features of CICIDS2017 Dataset,” accessed on                    24,           2025.       [Online].  Available: https://www.researchgate.net/figure/This-chart-highlights-the- top-10-features-in-the-CICIDS2017-dataset-based-on- their_fig3_377248675
  37. Kaggle, “Network Intrusion Dataset (CIC-IDS-2017),” accessed on  24, 2025. [Online].  Available: https://www.kaggle.com/datasets/chethuhn/network-intrusion- dataset
  38. WhizHack, “How OT Cybersecurity Protects India’s Smart Cities from Emerging Threats,” accessed on Nov. 24, 2025. [Online]. Available: https://whizhack.com/blog/how-ot- cybersecurity-protects-indias-smart-cities-from-emerging-threats
  39. arXiv, “Securing Tomorrow’s Smart Cities: Investigating Software Security in Internet of Vehicles and Deep Learning Technologies,” accessed on Nov. 24, 2025. [Online]. Available: https://arxiv.org/abs/2407.16410
  40. IEEE Xplore, “Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research,” accessed on Nov. 24, 2025. [Online]. Available: https://ieeexplore.ieee.org/document/09875264
Ahead of Print Subscription Review Article
Volume 14
01
Received 26/12/2025
Accepted 13/02/2026
Published 27/04/2026
Publication Time 122 Days
1

Login


My IP

PlumX Metrics