Method for mobile internet malicious application software detection based on support vector machines

Abstract

The invention relates to a method for mobile internet malicious application software detection based on support vector machines and belongs to the technical field of information safety. Currently, mobile internet application software plays a more and more important role in daily life of people; however, the method for mobile internet malicious application software detection is not mature enough. According to the method, the monitored mobile internet application software is analyzed according to a hidden Markov model so that the similarity level of each software basic operation type relative to current software can be obtained and a similarity vector can be formed; the similarity vector is input to five SVM models trained according to different kernel functions and whether an output result shows that the monitored mobile internet application software is a malicious application or not is judged by a voting system. According to the method, the shortages that a malicious behavior is defined imperfectly and a training dataset is overlarge in the prior art are overcome, effective detection on the malicious application software is achieved, and the reliability is high.

Description

technical field [0001] The invention relates to a method for detecting malicious application software in the mobile Internet, more precisely, to a method for detecting malicious application software in the mobile Internet based on a support vector machine, and belongs to the technical field of information security for malicious analysis of application software in the mobile Internet environment. Background technique [0002] With the advent of the mobile Internet era, the performance of mobile intelligent terminals is becoming more and more powerful, and the popularity is also increasing. In addition, the world is promoting the development of 3G and even 4G mobile networks. The high speed of mobile networks provides smart phone applications with the environment. Users start to consume music, electronic products, movies, maps, games and other applications on mobile smart terminals, and also use mobile smart terminals to communicate, such as social networks Facebook, Twitter, ...

AI Technical Summary

Problems solved by technology

In terms of software, various network security vendors, such as Symantec, Kaspersky, Trend Micro, etc., have begun to devote themselves to security solutions for smart mobile terminals, and domestic companies such as Rising have also begun to conduct research on related products, but the technology still in an incomplete stage

[0004] Similar to the security problems encountered by traditional computers, mobile smart terminals have also encountered the same problems. Viruses, malicious programs, Trojan horses, etc. have also begun to appear on terminals, bringing many violations to end users.

This detection method is the solution used to scan and kill viruses on computers. Its disadvantage is that it cannot detect unknown viruses and requires an update of the virus database. This is a huge problem for terminal devices with slow processing speed and limited resources. challenges, further research is needed

However, most related products in China are still in the stage of free download and use, and many key technologies are not yet mature.

[0008] To sum up, the role of mobile Internet application software in people's life is becoming more and more important, while the detection method of mobile Internet malicious application software is not mature enough.

Images