Evaluation of Secular Changes in Statistical Features of Traffic for the Purpose of Malware Detection
Applications and malware affecting them are dramatically changing. It isn’t certain whether the currently used features can classify normal traffic or malware traffic correctly. In this paper, we evaluated the features used in previous studies while taking into account secular changes to classify normal traffic into the normal category and anomalous traffic into the anomalous category correctly. A secular change in this study is a difference in a feature between the date the training data were caputred and the date the test data were captured in the same circumstance. The evaluation is based on the Euclidean distance between the normal codebook or anomalous codebook made by vector quantization and the test data. We report on what causes these secular changes and which features with little or no secular change are effective for malware detection.
Unable to display preview. Download preview PDF.
- 1.Internetthreatmonthlyreport (May 2011), http://ip.trendmicro.com/jp/threat/security_news/monthlyreport/article/20110602082147.html
- 2.Fujiwara, M., Terada, M., Abe, T., Kikuchi, H.: Study for the classification of malware by infectionactivities. In: IPSJCSEC, vol. 21, pp. 177–182 (March 2008) (in Japanese)Google Scholar
- 3.Ichino, M., Sakano, H., Komatsu, N.: Speaker Recognition Using Kernel Mutual Sbuspace Method, Thetransactions of the Institute of Electronics. Information and Communication Engineers 88(8), 1331–1338 (2005)Google Scholar
- 4.Karamcheti, V., Geiger, D., Kedem, Z., Muthukrishan, S.M.: Detecting malicious network traffic usinginverse distributions of packet contents. In: The ACM SIGCOMM Workshop on Mining Network Data, pp. 165–170 (2005)Google Scholar
- 5.Hatada, M., Nakatsuru, I., Akiyama, M.: Datasets for Anti-Malware Resarrch-MWS2011Datases-, MWS2011 (October 2011) (in Japanese)Google Scholar
- 6.Sato, Y., Waizumi, Y., Nemoto, Y.: Improving Accuracy of Network-basedanomalous Detection Using Multiple Detection Modules. Technical Commiteeon Network Systems (2004) (in Japanese)Google Scholar
- 7.Hiramatsu, N., Waizumi, Y., Tsunoda, H., Nemoto, Y.: Using Multiple Normal States for Network Anomaly Detection. In: IEICE (2006) (in Japanese)Google Scholar
- 8.Kugisaki, Y., Kasahara, Y., Hori, Y., Sakurai, K.: Study for botnet detection based on behavior observation of datatransmission interval. In: SCIS (2009) (in Japanese)Google Scholar