AI-Powered Aerial Automated Threat Detection and Secure Evidence Verification System: Literature Review

Author

Dr. Snehal S. Golait, Moreshwar Pachbhai, Anshul Umbarkar, Tanvi Honade, Kapil Hokarne

Abstract

 This paper gives a short review on AI-powered aerial threat detection and secure evidence verification using unmanned aerial vehicles (UAVs). With the increasing use of drones for surveillance, monitoring, and security applications, aerial images are becoming an important source of information and evidence. However, these images can be modified after capture, while AI-based detection models can also be affected by adversarial attacks. Therefore, simply detecting objects in a drone image is not enough to ensure that the obtained information is reliable and trustworthy. This review discusses different approaches for improving the reliability of UAV-based evidence, including SHA-256 image integrity verification, image tampering detection, adversarial attack detection, YOLO-based object detection, confidence verification, and pattern recognition. It also examines the importance of secure evidence logging and maintaining the traceability of image-processing operations. Recent research shows that image-forensic methods can help identify manipulated content, while lightweight and multi-scale deep-learning models can improve object detection in challenging aerial environments. Based on these findings, an integrated approach combining image security, AI-based detection, and secure evidence management can provide a more reliable foundation for UAV surveillance systems. The review also highlights challenges such as small objects in aerial images, changing environmental conditions, limited computational resources, evolving adversarial attacks, and the need for better datasets and real-world evaluation.

Keywords

Unmanned Aerial Vehicles , Aerial Surveillance, Automated Threat Detection, Real-time Object Detection, Anomaly Detection in Surveillance

Full Text:

Download Paper PDF

References

 [1] H. Shakhatreh, A. Sawalmeh, A. Al-Fuqaha, Z. Dou, E. Almaita, I. Khalil, N. S. Othman, A. Khreishah, and M. Guizani, “Unmanned Aerial Vehicles: A Survey on Civil Applications and Key Research Challenges,” IEEE Access, vol. 7, pp. 48572–48634, 2019.

 [2] F. E. Salamh, U. Karabiyik, M. K. Rogers, and E. T. Matson, “A Comparative UAV Forensic Analysis: Static and Live Digital Evidence Traceability Challenges,” Drones, vol. 5, no. 2, p. 42, 2021, doi: 10.3390/drones5020042.

[3] P. Duszejko, T. Walczyna, and Z. Piotrowski, “Detection of Manipulations in Digital Images: A Review of Passive and Active Methods Utilizing Deep Learning,” Applied Sciences, vol. 15, no. 2, p. 881, 2025, doi: 10.3390/app15020881.

[4] U. Tariq, T. A. Ahanger, and I. Ahmed, “Systematic Review of Trends in Deep Learning for UAV Cybersecurity,” Frontiers in Artificial Intelligence, vol. 9, Art. 1752124, 2026, doi: 10.3389/frai.2026.1752124.

[5] J. Qu, Q. Li, J. Pan, M. Sun, X. Lu, Y. Zhou, et al., “SS-YOLOv8: Small-size object detection algorithm based on improved YOLOv8 for UAV imagery,” Multimedia Systems, vol. 31, p. 42, 2025, doi: 10.1007/s00530-024-01622-3.

[6] Z. Wang, J. Lin, Y. Han, and Y. Pang, “Enhancing UAV aerial small target detection with bidirectional dynamic multi-scale attention YOLO,” The Visual Computer, vol. 42, p. 227, 2026, doi: 10.1007/s00371-026-04404-2.

[7] J. Qiu, F. Cai, N. Fu, and Y. Yao, “YOLO-Air: An Efficient Deep Learning Network for           Small Object Detection in Drone-Based Imagery,” IEEE Access, vol. 13, pp. 79718–79735, 2025, doi: 10.1109/ACCESS.2025.3565560.

[8] J. Ge, H. Lv, Y. Guo, Y. Chen, Y. Xu, and X. Yang, “MFR-YOLO: advancing UAV object detection with multi-scale feature refinement via deformable convolution and global attention,” Scientific Reports, vol. 16, Art. no. 15587, 2026, doi: 10.1038/s41598-026-45641-8.

[9] M. Li, H. Li, J. Zhu, and X. Zhang, “Visual Detection Algorithms for Counter-UAV in Low-Altitude Air Defense,” Computers, Materials & Continua, vol. 86, no. 3, p. 32, 2026, doi: 10.32604/cmc.2025.072406.

[10] D. R. Clark, C. Meffert, I. Baggili, and F. Breitinger, “DROP (DRone Open source Parser) your drone: Forensic analysis of the DJI Phantom III,” Digital Investigation, vol. 22, pp. S3–S14, 2017, doi: 10.1016/j.diin.2017.06.013.

Share your valuable work from Social Media Buttons