ORIGINAL ARTICLE
Security threats and risks in Edge AI
1
Katedra Cyberbezpieczeństwa, Politechnika Opolska, Polska
2
TECH, Nokia Solutions and Networks, Polska
Submission date: 2025-12-10
Acceptance date: 2026-04-08
Publication date: 2026-05-18
Rozprawy Społeczne/Social Dissertations 2026;20(1):97-107
KEYWORDS
TOPICS
ABSTRACT
Abstract: The aim of this article is to conduct a comprehensive analysis of security threats
affecting end devices in Edge AI environments, with particular emphasis on their specific
vulnerabilities resulting from architectural and technical limitations. Material and methods: The study was based on a review of the literature and the
latest reports on Edge AI security. The STRIDE methodology was used for the systematic
identification and classification of threats, analyzing all layers of the distributed AI
systems architecture (edge, fog, cloud). Results: A wide spectrum of hardware, software, and operational threats was identified,
including unique risks related to physical access to devices, manipulation of AI models,
and data leakage. Conclusions: Recommendations were formulated regarding protection mechanisms
covering authentication, cryptography, monitoring, and redundancy. The need to
continuously adapt security strategies to evolving attack techniques was emphasized as
a prerequisite for ensuring the reliability of Edge AI systems.
REFERENCES (21)
1.
Beerman, J., Berent, D., Falter, Z., Bhunia, S. (2023). A Review of Colonial Pipeline Ransomware Attack. 2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW), Bangalore, 8-15. https://doi.org/10.1109/ccgrid....
2.
Ferrag, M. A., Friha, O., Hamouda, D., Maglaras, L., Janicke, H. (2022). Edge-IIoTset: A New Comprehensive Realistic Cyber Security Dataset of IoT and IIoT Applications for Centralized and Federated Learning. IEEE Access, 10, 40281-40306. https://doi.org/10.1109/ACCESS....
3.
Ghadiri, R., ElHajj, M. (2023). Security and Performance Analysis of Edge Computing in IoT. IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2023, Malang, 542-548. https://doi.org/10.1109/COMNET....
4.
Gubbi, K. I., Kaur, I., Hashem, A., Sai Manoj, P. D., Homayoun, H., Sasan, A., Salehi, S. (2023). Securing AI Hardware: Challenges in Detecting and Mitigating Hardware Trojans in ML Accelerators. IEEE 66th International Midwest Symposium on Circuits and Systems (MWSCAS), Tempe, 821-825. https://doi.org/10.1109/MWSCAS....
5.
Jones, N. F. (2025). Decentralized Edge-AI Strategies for Micro-Datacenter Optimization and Resource-Conscious Query Execution. International Journal of Information Technology Research and Development (IJITRD), 6(3), 19-24.
6.
Kazimierczak, M., Habib, N., Chan, J. H., Thanapattheerakul, T. (2024). Impact of AI on the Cyber Kill Chain: A Systematic Review. Heliyon, 10(24), e40699. https://doi.org/10.1016/j.heli....
7.
Li, G., Hari, S. K. S., Sullivan, M., Tsai, T., Pattabiraman, K., Emer, J., Keckler, S. W. (2017). Understanding error propagation in deep learning neural network (DNN) accelerators and applications. SC ‘17: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, Denver, 1-12. https://doi.org/10.1145/312690....
8.
Marshall, A., Parikh, J., Kiciman, E., Shankar, R., Kumar, S. (2025). Threat Modeling AI/ML Systems and Dependencies. Microsoft. Pobrane z: https://learn.microsoft.com/en... (data dostępu 10.02.2025).
9.
Mukherjee, R., Chakraborty, R. S. (2022). Novel hardware trojan attack on activation parameters of FPGA-based DNN accelerators. IEEE Embedded Systems Letters, 14(3), 131-134. https://doi.org/10.1109/LES.20....
10.
Shafee, A., Hasan, S. R., Awaad, T. A. (2025). Privacy and security vulnerabilities in edge intelligence: An analysis and countermeasures. Computers and Electrical Engineering, 123, 110146. https://doi.org/10.1016/j.comp....
11.
Shi, W., Cao, J., Zhang, Q., Li, Y., Xu, L. (2016). Edge Computing: Vision and Challenges. IEEE Internet of Things Journal, 3(5), 637-646. https://doi.org/10.1109/JIOT.2....
13.
Singh, R., Gill, S. S. (2023). Edge AI: A survey. Internet of Things and Cyber-Physical Systems, 3. https://doi.org/10.1016/j.iotc....
14.
Strickland, E. (2024). 15 Graphs That Explain the State of AI in 2024: The AI Index Tracks the Generative AI Boom, Model Costs, and Responsible AI Use. IEEE Spectrum. Pobrane z: https://spectrum.ieee.org/ai-i... (data dostępu 10.02.2025).
15.
Sung, J., Han, S. (2024). Use of edge resources for DNN model maintenance in 5G IoT networks. Cluster Computing, 27(4), 5093-5105. https://doi.org/10.1007/s10586....
16.
Tuli, S., Mirhakimi, F., Pallewatta, S., Zawad, S., Casale, G., Javadi, B., Yan, F., Buyya, R., Jennings, N. R. (2023). AI augmented Edge and Fog computing: Trends and challenges. Journal of Network and Computer Applications, 216, 103648. https://doi.org/10.1016/j.jnca....
17.
von der Assen, J., Sharif, J., Feng, Ch., Bovet, G., Stiller, B. (2024). Asset-driven Threat Modeling for AI-based Systems. arXiv preprint. https://arxiv.org/html/2403.06....
18.
Wingarz, S., Lauscher, A., Edinger, J., Kaaser, D., Schulte, S., Fischer, M. (2024). SoK: Towards Security and Safety of Edge AI. arXiv preprint. https://arxiv.org/html/2410.05....
19.
Yi, S., Li, C., Li, Q. (2015). A Survey of Fog Computing. Mobidata ‘15: Proceedings of the 2015 Workshop on Mobile Big Data Pages, 37-42. https://doi.org/10.1145/275738....
20.
Zambare, P., Thanikella, V. N., Liu, Y. (2025). Securing agentic ai: Threat modeling and risk analysis for network monitoring agentic ai system. arXiv preprint. https://arxiv.org/html/2508.10....
21.
Zhao, K., Li, L., Ding, K., Gong, N. Z., Zhao, Y., Dong, Y. (2025). A systematic survey of model extraction attacks and defenses: State-of-the-art and perspectives. arXiv preprint. https://arxiv.org/html/2508.15....
Share
RELATED ARTICLE
| eISSN: | 2657-9332 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
