计算机科学 ›› 2017, Vol. 44 ›› Issue (Z6): 380-384.doi: 10.11896/j.issn.1002-137X.2017.6A.086
周宇欢,蒋大伟,龚勇,陈聪
ZHOU Yu-huan, JIANG Da-wei, GONG Yong and CHEN Cong
摘要： 为了在不解密加密数据的前提下获取加密数据流的类型信息,提出一种基于数据随机性特征和模式识别的加密数据流识别方法。该方法利用加密数据与非加密数据,或者不同类型加密数据0,1分布的随机性特性作为分类特征,再利用模式识别方法对不同数据进行建模,从而实现对不同类型数据的自动识别。首先利用NIST随机性测试方法对数据流进行分析,将得到的15类随机性测试得分作为分类特征；然后对不同类型的数据流分别建立分类模型；最后利用训练好的数据模型对未知数据流进行识别。仿真实验显示,与仅用单个随机性特征进行明密数据识别相比,采用模式识别方法可以将错分率由原来的60%以上下降到30%左右；进一步利用滤波器方法对15类随机性特征进行优化降维,平均错分率进一步下降到15%左右。
| [1] SOTO J.Statistical Testing of Random Number Generators.http://www.nist.gov. [2] RUKHIN A,SOTO J.A Statistical Test Suite for Random and Pseudorandom Number Generators for Cryptographic Applications [DB/OL].http://www.nist.gov. [3] SOTO J.Randomness Testing of the AES Candidate Algorithms .http://www.nist.gov. [4] HUANG G B,ZHU Q Y,SIEW C K.Extreme Learning Ma-chine:A New Learning Scheme of Feedforward Neural Networks[C]∥Proceedings of International Joint Conference on Neural Networks (IJCNN2004).Budapest,Hungary,July,2004:25-29. [5] HUANG G B,ZHU Q Y,SIEW C K.Extreme learning ma-chine:Theory and applications[J].Neurocomputing,2006,70(1-3):489-501. [6] HUANG G B,ZHOU H,DING X,et al.Extreme learning ma-chine for regression and multiclass classification[J].IEEE Transactions on Systems,Man,and Cybernetics,Part B:Cybernetics,2012,42(2):513-529. [7] MICHE Y,SORJAMANN A,BAS P,et al.OP-ELM:optimally pruned extreme learning machine[J].IEEE Transactions on Neural Networks,2010,21(1):158-162. [8] KIM M S,YU H J,KWAK K C,et al.Robust text-independent speaker identification using hybrid PCA & LDA[C]∥MICAI’ 06.Mexico,Nov.2006:1067-1074. [9] LIU C.Gabor-based kernel PCA with fractional power polynomial models for face recognition[J].IEEE Trans,Pattern Analysis and Machine Intelligence,2004,26(5):573-581. |
| No related articles found! |
|
||
首页