Towards Intelligent Security Mechanisms for Connected Things

• Paulo Freitas de Araujo-Filho UFPE / Université du Québec
• Divanilson R. Campelo UFPE
• Georges Kaddoum Université du Québec

DOI: https://doi.org/10.5753/sbrc_estendido.2024.1488

Abstract

The widespread adoption of connected devices and the adoption of machine learning enable attackers to launch several cyber-attacks and adversarial attacks. Therefore, the goals of this thesis are to investigate and develop cutting-edge solutions to enhance the security of systems by effectively and efficiently detecting cyber-attacks while also defending systems that rely on ML from adversarial attacks. The main results of our thesis comprehend multiple awards, the publication of eight papers in prestigious journals, three conference papers, two patents, and one software registration. Furthermore, our research has been recognized and awarded as one of the two 2022 Microsoft Research Ph.D. Fellowship recipients in Security, Privacy, and Cryptography worldwide.

References

Nisioti, A., Mylonas, A., Yoo, P. D., and Katos, V. (2018). From Intrusion Detection to Attacker Attribution: A Comprehensive Survey of Unsupervised Methods. IEEE Commun. Surveys & Tut., 20(4):3369–3388.

Pourranjbar, A., Elleuch, I., Landry-pellerin, S., and Kaddoum, G. (2023). Defense and Offence Strategies for Tactical Wireless Networks Using Recurrent Neural Networks. IEEE Trans. on Veh. Technol., pages 1–6.

Pourranjbar, A., Kaddoum, G., and Saad, W. (2022). Recurrent Neural Network-based Anti-jamming Framework for Defense Against Multiple Jamming Policies. IEEE Internet of Things J., pages 1–1.

Yuan, X., He, P., Zhu, Q., and Li, X. (2019). Adversarial examples: Attacks and defenses for deep learning. IEEE Trans. on Neural Netw. and Learn. Syst., 30(9):2805–2824.