论文标题
使用权限功能排名的Android恶意软件检测
Android Malware Detection using Feature Ranking of Permissions
论文作者
论文摘要
我们调查了使用Android权限作为工具，以便在良性和恶意软件应用程序之间进行快速有效的区分。为此，我们提取所有Android权限，消除那些具有零影响的Android权限，并应用两个特征排名算法，即卡方测试和Fisher的精确测试来对其进行排名和筛选，从而产生相对较小的相关权限。然后，我们使用决策树，支持向量机和随机森林分类器算法来检测恶意软件应用程序。我们的分析表明，与其他报道的方法相比，这种方法可以带来更好的准确性和F得分值。特别是，当随机森林与Fisher的精确测试结合使用作为分类器时，我们的准确性为99.34％，F-SCORE的fister form \％\％\％\％\％\％，相关数据集的误光率为0.56 \％，结果在准确性中的5.28 \％降低为99.82 \％，而frafe fals fals and falty fals and fals fals false and fals false则是95.28 \ \％，而f s \ falweration则为95.28 \ \％。考虑了流行的恶意软件系列。
We investigate the use of Android permissions as the vehicle to allow for quick and effective differentiation between benign and malware apps. To this end, we extract all Android permissions, eliminating those that have zero impact, and apply two feature ranking algorithms namely Chi-Square test and Fisher's Exact test to rank and additionally filter them, resulting in a comparatively small set of relevant permissions. Then we use Decision Tree, Support Vector Machine, and Random Forest Classifier algorithms to detect malware apps. Our analysis indicates that this approach can result in better accuracy and F-score value than other reported approaches. In particular, when random forest is used as the classifier with the combination of Fisher's Exact test, we achieve 99.34\% in accuracy and 92.17\% in F-score with the false positive rate of 0.56\% for the dataset in question, with results improving to 99.82\% in accuracy and 95.28\% in F-score with the false positive rate as low as 0.05\% when only malware from three most popular malware families are considered.
