Multi-feature fusion phishing webpage detection method

Abstract

The invention relates to a multi-feature fusion phishing webpage detection method, which comprises two parts such as a training process and a detection process. The multi-feature fusion phishing webpage detection method integrates three views of phishing webpage characteristics by combining a semi-supervised learning tri-training method, and mainly solves a problem that the existing phishing webpage detection methods mostly need to perform classification model training by using supervised learning through a large amount of annotation data. The method provided by the invention mainly combines a coordinated training algorithm, starts from webpage URL characteristics, webpage information characteristics and webpage search information characteristics, applies the idea of multiple views and multiple classifiers to phishing webpage detection, and achieves the purposes of reducing the total numbers of manual annotation training samples and timely recognizing a phishing webpage through coordinated training and learning of different classifiers.

Description

technical field [0001] The invention relates to a method for detecting phishing webpages, which mainly matches and recognizes phishing webpages from three characteristic views of URL, page and search information combined with a tri-training semi-supervised learning method, and belongs to the intersection field of information security and data mining. Background technique [0002] Today, with the rapid development of the Internet, the rise of e-commerce and the popularity of Internet payment, Internet commerce has become an indispensable part of more and more people's life and work. However, just under the background of the rapid development of Internet payment, the security situation of Internet payment is also becoming more and more serious. Among them, phishing attack, referred to as phishing, is an online identity forgery attack with the most serious harm and the highest success rate among various forms of Internet fraud. Criminals mainly use visual effects to imitate sp...

AI Technical Summary

Problems solved by technology

The existing phishing webpage detection technology is mainly based on blacklist mechanism and machine learning technology, and there are still some problems in the model construction: (1) Blacklist-based detection mechanism is the main means of browser security protection at present, but blacklist-based The establishment of the list database mainly relies on heuristic learning, manual reporting, and manual verification to determine that it takes a certain amount of labor costs and is easily affected by subjective factors. Secondly, the update of the blacklist database also has a certain lag, and it is difficult to meet large-scale The need for timely detection under phishing; (2) Most of the existing phishing web page detection methods based on machine learning use supervised learning methods to build classification models. Supervised learning methods can only use labeled data for training. In order to ensure the generalization of learning Due to the short life cycle of phishing websites, it is difficult and time-consuming to obtain labeled data.

Images