Evaluation of Secular Changes in Statistical Features of Traffic for the Purpose of Malware Detection
- Cite this paper as:
- Kawamoto K., Ichino M., Hatada M., Otsuki Y., Yoshiura H., Katto J. (2013) Evaluation of Secular Changes in Statistical Features of Traffic for the Purpose of Malware Detection. In: Lee R. (eds) Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing 2012. Studies in Computational Intelligence, vol 443. Springer, Berlin, Heidelberg
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.