Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195520,
        author = {Y MANOHAR REDDY and K. Dhruv Sharma and P. Gnan Aman and B. Sai Sri Vallabha},
        title = {Next-Generation AI-Driven Cybersecurity Framework for Flying Taxis Using Intrusion Detection and Secure Command Validation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {1371-1377},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195520},
        abstract = {Urban Air Mobility (UAM) operates as an advanced transportation system which enables cities with high population density to achieve better passenger movement outcomes while decreasing road traffic. The emerging ecosystem depends on flying taxis which are known as electric Vertical Take-Off and Landing (eVTOL) vehicles.
The operation of these vehicles depends on digital technologies which include GPS navigation systems and wireless communication networks and automated flight control systems and cloud- based monitoring platforms.
The increasing use of digital systems that connect to each other makes flying taxi systems more vulnerable to various cyber security risks. Attackers may attempt to manipulate navigation signals through GPS spoofing, inject malicious commands into the flight control system, or launch network-based intrusions to disrupt communication channels. Cyber-attacks targeting these systems will result in severe security breaches which endanger passenger safety and cause operational disruptions and create risks of operational disasters.
The research introduces a next-generation AI-based cybersecurity framework which protects flying taxi systems by reinforcing both their security measures and operational reliability. The security system uses machine learning technology to build an Intrusion Detection System (IDS) which detects unauthorized access attempts while deep learning technology creates an autoencoder model to detect GPS spoofing. The system uses RSA encryption to secure communications between different system components while verifying command execution through encrypted command validation.
The security alert system uses a dashboard which provides real-time information about security alerts and system health status and system alerts which show detected attack patterns. Index Terms—Urban Air Mobility, Flying Taxi Security, UAV Cybersecurity, Intrusion Detection System, GPS Spoofing Detec- tion, Autoencoder, RSA Encryption},
        keywords = {Urban Air Mobility, Flying Taxi Security, UAV Cybersecurity, Intrusion Detection System, GPS Spoofing Detection, Autoencoder, RSA Encryption},
        month = {April},
        }