Intelligent file scoring system for malware detection from the gray list

Abstract

Currently, the most significant line of defense against malware is anti-virus products which focus on authenticating valid software from a white list, blocking invalid software from a black list, and running any unknown software (i.e., the gray list) in a controlled manner. The gray list, containing unknown software programs which could be either normal or malicious, is usually authenticated or rejected manually by virus analysts. Unfortunately, along with the development of the malware writing techniques, the number of file samples in the gray list that need to be analyzed by virus analysts on a daily basis is constantly increasing. In this paper, we develop an intelligent file scoring system (IFSS for short) for malware detection from the gray list by an ensemble of heterogeneous base-level classifiers derived by different learning methods, using different feature representations on dynamic training sets. To the best of our knowledge, this is the first work of applying such ensemble methods for malware detection. IFSS makes it practical for virus analysts to identify malware samples from the huge gray list and improves the detection ability of anti-virus software. It has already been incorporated into the scanning tool of Kingsoft's Anti-Virus software. The case studies on large and real daily collection of the gray list illustrate that the detection ability and efficiency of our IFSS system outperforms other popular scanning tools such as NOD32 and Kaspersky.

A Survey on Malware and Malware Detection Systems

“…False positive is a malware detected while it is not malware and false negative is a benign program detected while it is not benign [3].…”

“…For the undecidable software, so-called gray list, the scanners operate them in a controlled environment for more classification [3].…”

“…But the main disadvantage with signature-based techniques is that they cannot defend against unknown malware [3] .…”

“…Thousands of new malware appear very quickly, reports from G Data and King soft Laboratory said [2,3]. In contrast, researchers and manufacturers evolve new methods to produce improved techniques for building anti-malware [4][5][6][7][8].…”

“…And sometimes it's tasks divided into client and server, such as in cloud-based antivirus [8,12]. Many improvements made on both aspects of detection and analysis [3,10,[13][14][15][16][17].…”