Malware has been the primary threat to computer and network for years. Traditionally, supervised learning methods are applied to detect malware. But supervised learning models need a great number of labeled samples to train models beforehand, and it is impractical to label enough malicious code manually. Insufficient training samples yields imperfect detection models and satisfactory detection result could not be obtained as a result. In this paper, we bring out a new algorithm call ColSVM (Collaborative Support Vector Machine) based on semi-supervised learning and independent component analysis. With ColSVM, only a few labeled samples is needed while the detection result keeps in a high level. Besides, we propose a general framework with independent components analysis, with which to reduce the restricted condition of collaborative train. Experiments prove the efficiency of our model finally.
Zhang, K., Li, C., Wang, Y., Zhu, X., & Wang, H. (2017). Collaborative Support Vector Machine for Malware Detection. In Procedia Computer Science (Vol. 108, pp. 1682–1691). Elsevier B.V. https://doi.org/10.1016/j.procs.2017.05.063