High Precision Screening for Android Malware with Dimensionality Reduction
High Precision Screening for Android Malware with Dimensionality Reduction
复制标题
DOI：
10.1109/icmla.2014.10
复制
发表时间：
2014-12
期刊：
影响因子：
--
通讯作者：
B. Wolfe;Karim O. Elish;D. Yao
中科院分区：
文献类型：
--
作者：
B. Wolfe;Karim O. Elish;D. Yao
我们提出了一种新的方法，将以前看不见的Android应用程序分类为恶意软件或良性的。该算法从一个大的特征集开始：应用程序字节码中所有可能的n字节序列的频率。主成分分析应用于该频率矩阵，以将其减少到低维表示，然后将其馈送到几种分类算法中的任何一种。我们利用隐式重新启动的Lanczos双对角化算法，并利用稀疏的n-gram频率矩阵，以有效地计算低维表示。当在低维表示上训练时，几种分类算法比以前的工作实现了更高的准确性。
We present a new method of classifying previously unseen Android applications as malware or benign. The algorithm starts with a large set of features: the frequencies of all possible n-byte sequences in the application's byte code. Principal components analysis is applied to that frequency matrix in order to reduce it to a low-dimensional representation, which is then fed into any of several classification algorithms. We utilize the implicitly restarted Lanczos bidiagonalization algorithm and exploit the sparsity of the n-gram frequency matrix in order to efficiently compute the low-dimensional representation. When trained upon that low-dimensional representation, several classification algorithms achieve higher accuracy than previous work.