| 引用本文： |
-
余建昌,张弘,尤玮珂,赵险峰.基于分析CAVLC码字和非零QDCT系数个数的视频隐写分析方法[J].信息安全学报,已采用 [点击复制]
- yujianchang,zhanghong,youweike,zhaoxianfeng.Video Steganalysis Considering CAVLC Codewords and the Number of Nonzero QDCT Coefficients[J].Journal of Cyber Security,Accept [点击复制]
|
|
| 摘要: |
| 针对H.264量化离散余弦变换(Quantized Discrete Cosine Transform, QDCT)系数域的视频隐写方法，本文提出了一种高效的隐写分析方法。目前已有的QDCT系数域的隐写分析方法大多关注嵌入前后QDCT系数的变化。但QDCT系数存在一些冗余信息，已有的分析方法已无法有效检测近年来出现的QDCT系数域上的自适应隐写方法。H.264中使用熵编码对QDCT系数进行无损压缩，去除冗余信息。上下文自适应可变长度编码(Context-based Adaptive Variable Length Coding, CAVLC)是H.264中熵编码的两种方式之一，相比于另一种熵编码方式上下文自适应二进制算术编码(Context-based Adaptive Binary Arithmetic Coding, CABAC)，CAVLC计算复杂度低且支持H.264所有档次。因此，首先本文基于CAVLC编码的原理，分析了嵌入修改对CAVLC编码过程中的影响和最终体现在对CAVLC码字的影响。其次，因为相邻块非零QDCT系数个数之间具有相关性，本文分析了修改QDCT系数对此相关性的影响。最终，本文设计了一个635维度的隐写分析特征集，其包括两类子特征。第一个子特征为码字中“1”的比例和码字中每个比特上“1”的比例，用于描述CAVLC码字；第二个子特征为给定当前块中非零QDCT系数的个数，其右侧块的和下方块的非零QDCT系数个数的分布概率，该概率反映了相邻块的非零QDCT系数个数之间的相关性。为评估本文提出方法的有效性，对不同编码参数设置下的视频进行了实验测试。实验结果表明，该方法优于现有的QDCT系数域上的视频隐写分析方法,在较低嵌入率下也具有良好的检测性能，从而验证了本文特征设计的合理性。并且该方法在保证检测准确率提升的同时，其计算复杂度不高于现有的隐写分析方法。 |
| 关键词: H.264 视频隐写分析 量化离散余弦变换系数 上下文自适应可变长度编码 |
| DOI：10.19363/J.cnki.cn10-1380/tn.2023.08.27 |
| 投稿时间：2021-05-08修订日期：2021-08-04 |
| 基金项目:国家自然科学基金项目（面上项目，重点项目，重大项目） |
|
| Video Steganalysis Considering CAVLC Codewords and the Number of Nonzero QDCT Coefficients |
|
yujianchang, zhanghong, youweike, zhaoxianfeng
|
| (Institute of Information Engineering，Chinese Academy of Sciences) |
| Abstract: |
| In this paper, an effective steganalytic method is proposed to detect QDCT (Quantized Discrete Cosine Transform) Coef-ficient-based H.264 steganography. At present, most of the steganalytic methods pay attention to the changes of QDCT coefficients before and after embedding. Due to the redundant information in the QDCT coefficients, they cannot effec-tively detect the adaptive QDCT Coefficient-based H.264 steganographic methods in recent years. In the H.264, entropy coding is used to perform lossless compression on QDCT coefficients to remove redundant information. CAVLC (Con-text-based Adaptive Variable Length Coding) is one of two forms of entropy coding in the H.264. Compared with another entropy coding method CABAC (Context-based Adaptive Binary Arithmetic coding), CAVLC has low computational complexity and supports all H.264 profiles. Therefore, based on the principle of CAVLC coding, this paper firstly analyzes the influence of embedding modification on the coding process of CAVLC and finally on the CAVLC codewords. Sec-ondly, because there is a correlation between the number of non-zero QDCT coefficients of adjacent blocks, this paper analyzes the impact of modifying the QDCT coefficient on this correlation. Finally, this paper designs a 635-dimensional steganalytic feature set, which includes two types of sub-features. The first sub-feature is the ratio of “1” in the codeword and the ratio of “1” in each bit in the codeword, which is used to describe the CAVLC codeword. The second sub-feature is the probability of the number of non-zero QDCT coefficients in the adjacent block(the blocks to the right of and below the current block) given the number of non-zero QDCT coefficients in the current block, the probability reflects the corre-lation between the number of non-zero QDCT coefficients of adjacent blocks. To evaluate the effectiveness of the pro-posed method, we carry out experiments on videos under different setups. The experimental results have demonstrated that the proposed method outperforms the prior methods of detecting QDCT coefficients modification in H.264 videos, also performs well even at low embedding strengths. The experimental results have verified the rationality of feature de-sign. Moreover, while ensuring the improvement of detection accuracy, the computational complexity of this method is not higher than that of the prior methods. |
| Key words: H.264 video steganalysis quantized discrete cosine transform coefficient context-adaptive variable length coding |
