博弈模型上的策略自适应隐写方法  

Strategic adaptive steganography based on the game theory model

作　　者：钮可[1] 李军[1,2] 刘佳[2] 杨晓元[1,2] 

机构地区：[1]密码与信息安全武警部队重点实验室,陕西西安710086 [2]武警工程大学网络与信息安全研究所,陕西西安710086

出　　处：《西安电子科技大学学报》2015年第4期165-170,共6页Journal of Xidian University

基　　金：国家自然科学基金资助项目(61379152)

摘　　要：在隐写博弈模型改进的基础上,提出了一种基于策略自适应的隐写方法.首先将图像变换到小波域,利用人眼视觉特性中的亮度掩蔽、频率掩蔽和纹理掩蔽效应计算失真测度函数;然后建立起基于内容自适应的失真测度函数与基于策略自适应的偏离函数之间的联系,并根据隐写博弈模型中的纳什均衡得到每一个载体嵌入秘密信息的概率,从而实现了基于策略自适应的图像隐写方法.实验结果表明,该方法的安全性高于基于内容自适应的HUGO算法.On the basis of the improvement of the game theory model , we propose a Strategic adaptive steganography method . First , we use the human visual characteristics of luminance masking , texture masking and the frequency masking factor to compute the distortion measure function after the image is transformed into the wavelet domain . Then we establish a connection between content adaptive distortion measure functionand the strategic adaptive bias function , so that we can get the probability of each cover element for embedding the message according to the Nash equilibrium in the game theory model for steganography . Experimental results show that the statistical security of the proposed method is high than that of the HUGO which is the method of content adaptive steganography .

关 键 词：隐写 博弈论 策略自适应 人眼视觉特性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]