Phishing Detection System Based on the SVM Active Learning Algorithm
Dai Tao, Du Jinran, Xu Aidong, Xu Chuanmao, Lai Boyu, Chao Hong · 2023
This paper takes the phishing detection system as the object of discussion. Through the conventional abnormal intrusion detection method, the system should be based on a large number of sample information to ensure the detection rate, but this is difficult to achieve for the actual network security protection detection conditions. In this regard, SVM active learning algorithm is selected in this paper to make up for the cost of high sample collection. For phishing attacks, URL is used as a breakthrough to identify and classify characteristic elements to achieve the purpose of effective detection of phishing. The experimental results show that this detection system can have good operation performance even in the face of small samples.