Intelligent virus detection on mobile devices
暂无分享，去创建一个
In this paper, we describe a new solution for detecting mobile phone viruses. The solution is based on Bayesian decision theory using heuristic rules derived from common functionalities among different virus samples. Specifically, we detect viruses according to the DLL usage of a program, which is directly linked to the functionality of this program. Our solution is able to detect unknown viruses, especially the variants of existing ones. We evaluate our solution on the Symbian platform, where most viruses are present in the wild. We constructed a virus detector based on DLL functions from a small set of virus samples. It detects 95% of mobile viruses and yields no false alarm.
[1] Zhiyong Lu,et al. Explaining Naive Bayes Classifications , 2003 .
[2] Gerald Tesauro,et al. Neural networks for computer virus recognition , 1996 .
[3] Peter Norvig,et al. Artificial Intelligence: A Modern Approach , 1995 .
[4] Peter Szor,et al. The Art of Computer Virus Research and Defense , 2005 .
[5] Salvatore J. Stolfo,et al. Data mining methods for detection of new malicious executables , 2001, Proceedings 2001 IEEE Symposium on Security and Privacy. S&P 2001.