基于共生特征和集成多超球面OC-SVM的JPEG隐密分析方法  

JPEG Steganalysis Based on Co-occurrence Features and Ensemble Multiple Hyperspheres OC-SVM

作　　者：郭艳卿[1] 孔祥维[1] 尤新刚[1,2] 

机构地区：[1]大连理工大学信息安全研究中心,大连116024 [2]北京电子技术应用研究所,北京100091

出　　处：《电子与信息学报》2009年第5期1180-1184,共5页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(60572111)资助课题

摘　　要：隐密是指将秘密信息以不可察觉的方式隐藏于其他载体之中的技术。隐密分析的目的是检测秘密信息的存在并最终提取秘密信息。目前基于二类或多类分类器的盲隐密分析方法可有效检测已知隐密算法,但无法对未公开隐密算法的生成图像进行检测。该文提出了一种新的JPEG盲隐密分析方法,对已知或未公开隐密算法都可检测。基于共生特征和多超球面OC-SVM分类器,本方法利用能有效对载体JPEG图像的统计分布边界建模。为进一步提高检测性能,还应用Bagging集成学习算法提高分类器的泛化能力。实验结果表明,该文方法能较为准确地检测出典型JPEG隐密算法生成的含密图像,性能优于已有的同类隐密分析方法。Steganography is the technology of hiding a secret message in plain sight. The goal of steganalysis is to detect the presence of embedded data and to eventually extract the secret message. Current blind steganalytic methods, which relied on two-class or multi-class classifier, have offered strong detection capabilities against known embedding algorithms, but they suffer from an inability to detect previously unknown forms of steganography. In this paper, a new JPEG blind steganalytic technique for detecting both known and unknown steganography is proposed. On the basis of co-occurrence features and multiple hyperspheres One-Class SVM（OC-SVM） classifier, the proposed method can effectively model the statistics distribution boundary of innocent JPEG images. Bagging ensemble learning algorithm is also used to achieve higher detecting performance. Experimental results show the superiority of the method over other analogous steganalytic techniques.

关 键 词：隐密分析 共生特征 多超球面 一类支持向量机 BAGGING 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]