Malicious PDF document detection method based on TF-IDF algorithm and SVDD algorithm

Abstract

The invention discloses a malicious PDF document detection method based on a TF-IDF algorithm and an SVDD algorithm. The method includes the following steps: 1) collecting malicious PDF documents andnormal PDF documents as sample sets; 2) generating a detection model capable of detecting the malicious PDF documents; and 3) detecting PDF documents to be detected. The malicious PDF documents and the normal PDF documents are collected as the sample sets in the step 1); suspicious JavaScript codes contained in the malicious PDF documents in the sample sets are positioned and extracted in the step2), the TF-IDF algorithm is adopted to perform malicious PDF document feature generation, and the SVDD algorithm is adopted to generate the PDF malicious document detection model and a discriminationfunction; and in the step 3), the judgment on the PDF documents to be detected through the detection model is achieved. According to the malicious PDF document detection method, the malicious PDF documents can be analyzed and detected accurately and efficiently, and serious hazards posed on personal and company property and privacy security by the malicious PDF documents are avoided.

Description

technical field [0001] The invention relates to the technical field of computer information security, in particular to a malicious PDF document detection method based on TF-IDF algorithm and SVDD algorithm. Background technique [0002] Portable Document Format (PDF) is an electronic file format designed by Adobe Systems to support cross-platform network information publishing and interaction. PDF documents have many characteristics: PDF is a non-related computer operating system Portable document format, which will not affect the normal editing and reading of documents due to different operating system environments; PDF also supports embedded font information, high-compression pictures and vector graphics, and can also contain hypertext connections, audio and dynamic multimedia information, It has high integration. It is precisely because of the above characteristics that PDF has become the normative standard for saving document materials. [0003] With the gradual popula...

AI Technical Summary

Problems solved by technology

[0005] The technical problem solved by the present invention: provide a malicious PDF document detection method based on TF-IDF algorithm and SVDD algorithm, to solve the problem that PDF documents are easily infected by JavaScript code because there is no special malicious PDF document detection method at present

Images