Dear Omar Alhuniti,

I would suggest you the following important topics:

Topic 1: Using Machine Learning Security in the Internet of Medical Things

Topic 2: Using Machine Learning in Software Defined Networks to Detect Malicious Activity

See my literature sources on these topics.

Much success

Anatol Badach

Mingfu Xue, Chengxiang Yuan, Heyi Wu, Yushu Zhang, Weiqiang Liu: „Machine Learning Security: Threats, Countermeasures, and Evaluations“; IEEE Access , Vol 8, April 2020, DOI: 10.1109/ACCESS.2020.2987435

https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9064510

https://ebin.pub/cyber-security-meets-machine-learning-9813367253-9789813367258.html

Topic 1:

Shilan S Hameed , Wan Haslina Hassan , Liza Abdul Latiff, Fahad Ghabban: „A systematic review of security and privacy issues in the internet of medical things; the role of machine learning approaches“; PeerJ Comput Sci, Mar 2021, DOI: 10.7717/peerj-cs.414

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8022640/

Arun Rana, Chinmay Chakraborty, Sharad Sharma, Sachin Dhawan, Subhendu Kumar Pani, Imran Ashraf: Internet of Medical Things-Based Secure and Energy-Efficient Framework for Health Care; Big Data, Vol. 10, No. 1, Feb 2022, DOI: 10.1089/big.2021.0202

https://www.liebertpub.com/doi/10.1089/big.2021.0202

Topic 2:

Yogita Hande, Akkalashmi Muddana: A Survey on Intrusion Detection System for Software Defined Networks (SDN); International Journal of Business Data Communications and Networking ; Vol 16, Issue 1, 2020; DOI: 10.4018/IJBDCN.2020010103 https://www.igi-global.com/gateway/article/245780

Ahnaf Ahmad, Erkki Harjula, Mika Ylianttila, Ijaz Ahmad: Evaluation of Machine Learning Techniques for Security in SDN; IEEE Xplore, March 2021; DOI: 10.1109/GCWkshps50303.2020.9367477 https://ieeexplore.ieee.org/document/9367477

You can use deem learning algorithms such as ANN, RNN, .. to identify eventual intrusion and attacks in IoT applications or 802.11 networks.

You can look at these papers

Preprint Reinforcement-Learning-Based IDS for 6LoWPAN

Article DETONAR: Detection of Routing Attacks in RPL-Based IoT

Machine learning can be applied in various ways in security, for instance, in malware analysis, to make predictions, and for clustering security events. It can also be used to detect previously unknown attacks with no established signature.