IoT Malicious Traffic Classification and Detection Using Machine Learning Algorithms

The Internet of Things (IoT) is one of today's most rapidly growing technologies. The exchange of data between IoT devices generates a large amount of information that needs to be shared. There is a potential for security breaches in these communications, which could be deliberately damaging to the connected devices. It is crucial to detect and deal with unauthorized communication and security breaches in order to avoid further harm and repercussions. The goal of this project is to differentiate deliberate communications from unsecure communications among the IoT devices. Different patterns can be observed in intentional communications compared to insecure communications. Machine learning based on artificial intelligence can be used to detect these patterns in intentional and insecure communication. The paper utilizes Random Forest, Decision Tree, and SVM to differentiate between patterns associated with intended and unintended messages. The performance of the machine learning approach proposed was evaluated by utilizing the Aposemat IoT-23 dataset, and it achieved a 99.25% accuracy when compared to the benchmark dataset. It is found that the suggested Random Forest approach performs better than the current ones when there are enough patterns to recognize. A potential solution to be applied on this dataset is also explored and proposed in order to improve the performance of the underperforming classifiers on the imbalanced dataset. Employing machine learning models makes it possible to detect and mitigate IoT malware threats, ultimately safeguarding the integrity and privacy of IoT devices and networks. This paper contributes to the growing body of knowledge in IoT security and provides a foundation for further research in this critical domain.

IoT Malicious Traffic Classification and Detection Using Machine Learning Algorithms Keywords:

IoT Devices , Machine learning , Artificial Intelligence , Traffic classification , Malware Analysis , IoT Security