| DBN和GRU混合的Android恶意软件检测模型 |
| |
| 引用本文： | 欧阳立,芦天亮,暴雨轩,李默. DBN和GRU混合的Android恶意软件检测模型[J]. 中国人民公安大学学报(自然科学版), 2020, 0(1): 104-108 |
| |
| 作者姓名： | 欧阳立 芦天亮 暴雨轩 李默 |
| |
| 作者单位： | 中国人民公安大学警务信息工程与网络安全学院 |
| |
| 基金项目： | 国家重点研发计划“网络空间安全”重点专项(2017YFB0802804);“十三五”国家密码发展基金密码理论研究重点课题(MMJJ20180108)。 |
| |
| 摘 要： | 针对Android平台恶意软件数量增长迅猛,种类日益增多的现状,提出了一种基于深度置信网络和门控循环单元网络混合的Android恶意软件检测模型。通过自动化提取Android应用软件的特征,包括权限等静态特征和应用运行时的动态特征进行训练,对Android恶意软件进行检测和分类。实验结果表明,混合了门控循环单元网络和深度置信网络的混合模型,在检测效果上优于传统的机器学习算法和深度置信网络模型。
|
| 关 键 词： | 安卓 恶意软件检测 深度置信网络 门控循环单元 |
Android Malware Detection Model Using Combined DBN and GRU |
| |
| OUYANG Li,LU Tianliang,BAO Yuxuan,LI Mo. Android Malware Detection Model Using Combined DBN and GRU[J]. Journal of the People's Public Security University(Natural Science Edition), 2020, 0(1): 104-108 |
| |
| Authors: | OUYANG Li LU Tianliang BAO Yuxuan LI Mo |
| |
| Affiliation: | (School of Police Information Engineering and Cyber Security,People s Public Security University of China,Beijing 100076,China) |
| |
| Abstract: | With the rapid growth of the number and variety of malwares on the Android platform,an Android malware detection model based on a mixture of deep belief networks and gated recurrent unit was proposed.The android malware is detected and classified by automatically extracting the features of Android application software,including static features such as permissions and dynamic features during application runtime.Experimental results show that the hybrid model with a gated recurrent unit network is superior to traditional machine learning algorithms and deep belief network models in detecting results. |
| |
| Keywords: | Android malware detection deep belief network gated recurrent unit |
| 本文献已被 CNKI 维普 等数据库收录！ |
