Key points are not available for this paper at this time.
Artificial Intelligence (AI) has become an integral part of modern-day solutions for its ability to learn very complex functions and handling"Big Data". However, the lack of explainability and interpretability of AI models is a key stumbling block when trust in a model's is critical. This leads to human intervention, which in turn results a delayed response or decision. While there have been major advancements in speed and performance of AI-based intrusion detection systems, the response still at human speed when it comes to explaining and interpreting a specific or decision. In this work, we infuse popular domain knowledge (i. e. , principles) in our model for better explainability and validate the on a network intrusion detection test case. Our experimental results that the infusion of domain knowledge provides better explainability as as a faster decision or response. In addition, the infused domain generalizes the model to work well with unknown attacks, as well as the path to adapt to a large stream of network traffic from numerous IoT.
Islam et al. (Thu,) studied this question.