AI Based Secure ATM Access and Intrusion Response System

The implementation results confirm that the system operates efficiently in real-time environments with low latency and high reliability. The automated response mechanisms, including solenoid lock activation and alarm triggering, provide immediate physical security control, making the system proactive rather than reactive.   Overall, the proposed solution offers a cost-effective, scalable, and intelligent framework for modern ATM security. It significantly improves threat detection accuracy, reduces dependency on human surveillance, and enhances overall system responsiveness. This makes it suitable for deployment in banking environments where security, speed, and reliability are critical requirements.

[1]. Degadwala, Sheshang, et al. “Advancements in ATM Security for Movement and Tampering Detection: A Review.” International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2024. Available at: https://doi.org/10.32628/CSEIT2410587. [2]. Sanserwal, Vishal, et al. “Comparative Analysis of Various Feature Descriptors for Efficient ATM Surveillance Framework.” Proceeding - IEEE International Conference on Computing, [3]. Communication and Automation, ICCCA 2017, 2017, pp. 539–44.Availableat: https://doi.org/10.1109/CCAA.2017.8229860. [4]. Liu, Fan, et al. “Abnormal Behavior Recognition System for ATM Monitoring by RGB-D Camera.” MM 2012 - Proceedings of the 20th ACM International Conference on Multimedia, 2012, pp. 1295 – 96. Available at: https://doi.org/10.1145/2393347.2396450. [5]. Wu J-D, Ye S-H (2009) Driver identification using finger-vein patterns with Radon transform and neural network. Expert SystAppl 36(3, Part 2):5793–5799. [6]. Researcher Wu and Liu have described neural network and component analysis methodology used in finger vein authentication method.