Detection of Web Attacks Using the BERT Model

This paper presents a web intrusion detection system that addresses security threats with the increasing use of web applications in almost all domains, as well as the increase in attacks against web applications. Our web intrusion detection system consists of a model that can distinguish between normal and abnormal URLs. In the URL analysis phase, our model uses the BERT model of Transformers, a prominent natural language processing technique. In the classification phase, we use a CNN model, which is a popular deep learning technique. We utilize the CSIC 2010, FWAF, and HttpParams datasets for training and testing. The experimental results show that our model performs the classification of normal and abnormal requests in 0.4 ms, which is an extremely fast detection time when compared to the reported results in the literature and an accuracy of over 96%.