CNN-based Steganalysis of MP3 Steganography in the Entropy Code Domain
CNN-based Steganalysis of MP3 Steganography in the Entropy Code Domain
复制标题
DOI：
10.1145/3206004.3206011
复制
发表时间：
2018-06
期刊：
影响因子：
--
通讯作者：
Yuntao Wang;Kun Yang;Xiaowei Yi;Xianfeng Zhao;Zhoujun Xu
中科院分区：
文献类型：
--
作者：
Yuntao Wang;Kun Yang;Xiaowei Yi;Xianfeng Zhao;Zhoujun Xu
本文提出了一种有效的基于CNN的隐写分析方案，用于在熵码域检测MP3的隐写。这些隐写方法通过霍夫曼码替换将秘密信息隐藏到压缩后的音频流中，通常具有容量大、安全性好、计算复杂度低等优点。首先，与以往大多数基于CNN的隐写分析方法不同，本文选择量化修正DCT （QMDCT）系数矩阵作为网络的输入数据。其次，采用高通滤波器提取剩余信号，并抑制内容本身，使网络对数据隐藏方法引入的细微变化更加敏感。第三，采用$ 1 \ × 1 $卷积核和批处理归一化层来减少过拟合的危险，加速反向传播的收敛。此外，通过对体系结构进行微调，优化了网络的性能。实验表明，本文提出的CNN的性能远远优于传统的手工特征。特别是对于一种自适应MP3隐写算法——等长熵码替换（EECS）算法的检测，该网络具有较好的性能，而传统的手工特征很难检测到这种算法。该网络可以无缝地应用于各种比特率和相对有效负载。最后，提出了一种滑动窗口方法来隐写任意大小的音频。
This paper presents an effective steganalytic scheme based on CNN for detecting MP3 steganography in the entropy code domain. These steganographic methods hide secret messages into the compressed audio stream through Huffman code substitution, which usually achieve high capacity, good security and low computational complexity. First, unlike most previous CNN based steganalytic methods, the quantified modified DCT (QMDCT) coefficients matrix is selected as the input data of the proposed network. Second, a high pass filter is used to extract the residual signal, and suppress the content itself, so that the network is more sensitive to the subtle alteration introduced by the data hiding methods. Third, the $ 1 \times 1 $ convolutional kernel and the batch normalization layer are applied to decrease the danger of overfitting and accelerate the convergence of the back-propagation. In addition, the performance of the network is optimized via fine-tuning the architecture. The experiments demonstrate that the proposed CNN performs far better than the traditional handcrafted features. In particular, the network has a good performance for the detection of an adaptive MP3 steganography algorithm, equal length entropy codes substitution (EECS) algorithm which is hard to detect through conventional handcrafted features. The network can be applied to various bitrates and relative payloads seamlessly. Last but not the least, a sliding window method is proposed to steganalyze audios of arbitrary size.