全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

Android运行时恶意行为检测模型研究

DOI: 10.13190/j.jbupt.2014.03.012

Keywords: 隐马尔可夫模型,支持向量机,恶意行为,智能终端

Full-Text   Cite this paper   Add to My Lib

Abstract:

为实现Android应用程序恶意行为的有效分析,提出了基于HMMs-SVM的程序行为分类模型,将隐马尔可夫模型(HMM)和支持向量机(SVM)相结合,以动态行为序列作为关键特征,对移动应用软件运行中的网络收发、文件访问等行为建模.该模型融合了HMM和SVM的优势,并克服了二者的不足,适合于在获取连续动态行为特征序列后进行行为分类.实验结果表明,该方法分析召回率较高,可以有效对应用中的异常行为进行捕捉,并可以将其按类型分类.

References

[1]  Bente I, Hellmann B, Vieweg J, et al. TCADS: trustworthy, context-related anomaly detection for smartphones[C]//15th International Conference on Network-Based Information Systems, 2012. Australia: IEEE, 2012: 247-254.
[2]  Shabtai A, Moskovitch R, Feher C, et al. Detecting unknown malicious code by applying classification techniques on OpCode patterns[J]. Security Informatics, 2012, 1(1): 1-22.
[3]  Li Qi, Zhang Miao, Xu Guoai. A novel element detection method in audio sensor networks[J]. International Journal of Distributed Sensor Network, 2013, Article ID 607187.
[4]  刘春波, 段雪涛, 贾春福. 基于层次隐马尔科夫模型和变长语义模式的入侵检测方法[J]. 通信学报, 2010(3): 109-114. Liu Chunbo, Duan Xuetao, Jia Chunfu. Intrusion detection method based on hierarchical hidden Markov model and variable-length semantic pattern[J]. Journal on Communications, 2010(3): 109-114.
[5]  Cristianini N, Shawe T J. An introduction to support vector machines and other kernel-based learning methods[M]. Cambridge: Cambridge University Press, 2000: 121-147.
[6]  Blasing T, Batyuk L, Schmidt A, et al. An android application sandbox system for suspicious software detection[C]//5th International Conference on Malicious and Unwanted Software, 2010. France: IEEE, 2010: 55-62.
[7]  Miettinen M, Halonen P, Hatonen K. Host-based intrusion detection for advanced mobile devices[C]//20th International Conference on Advanced Information Networking and Applications, 2006. Austria: IEEE, 2006: 72-76.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133