Fast Steganalysis Method for VoIP Streams

Yang, Hao; Yang, Zhongliang; Bao, YongJian; Liu, Sheng; Huang, Yudong

doi:10.1109/lsp.2019.2961610

Cited by 18 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In reference [34], Lin et al proposed a steganalysis network based on recurrent neural network (RNN). To reduce the time cost and improve the detection accuracy of the NNbased method, Yang et al [35] mapped vector quantization codewords into a semantic space and utilized one hidden layer to extract the corrections between the codewords. Yang et al [36] developed multi-channel convolutional sliding windows to analyze the correlations between a given frame and its neighboring frames.…”

Section: Related Workmentioning

confidence: 99%

Steganalysis of Compressed Speech Based on Global and Local Correlation Mining

et al. 2022

View full text Add to dashboard Cite

Most of the existing steganalysis methods are designed for specific steganography methods in low-bit-rate compressed speech stream and lack of generalization ability. In practical applications, the steganography methods in compressed speech are various and cannot be predicted in advance. We can only employ numerous possible steganalysis method to detect, which is laborious and time-consuming, and cannot achieve real-time detection. Therefore, it is necessary to develop a general steganalysis method that can detect multiple steganography methods simultaneously for compressed speech. To this end, we propose a steganalysis method based on global and local correlation mining in this paper. Firstly, we introduce a codeword distributed embedding module to transform the compressed codewords into a compact feature representation. Then, we propose global-guided correlation mining module and local-guided correlation mining module to extract the correlation change before and after steganography in the view of global and local. Finally, the detection results can be obtained by the full connection layers. Experimental results show that the proposed method can reach a better detection performance than the existing steganalysis methods at different embedding rates and speech lengths.

show abstract

Section: Related Workmentioning

confidence: 99%

Steganalysis of Compressed Speech Based on Global and Local Correlation Mining

et al. 2022

View full text Add to dashboard Cite

show abstract

“…To extract a more complicated steganalysis feature, Lin et al 27 put forward a codeword correlation model based on recurrent neural network (RNN), which applies RNN to capture four strong codeword correlation, including successive frame, intra‐frame, cross‐frame, and crossword correlations. To improve the detection efficiency, Yang et al 28 propose a fast steganalysis method, which first uses embedding technology to map the code words into a semantic space. Then, it utilizes one hidden layer to exploit the correlation between those code words.…”

Section: Related Workmentioning

confidence: 99%

“…To detect steganography for low‐bit‐rate speech streams, many researchers have put forward various methods 24–33 . For the PD domain, the distribution of the difference of PD would be changed after embedding secret information.…”

Section: Introductionmentioning

confidence: 99%

Towards blind detection of steganography in low‐bit‐rate speech streams

Sun

Tian

Mazurczyk

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

To prevent the abuse of low‐rate speech‐based steganography from threatening cyberspace security, the corresponding steganalysis approaches have been developed and received significant attention from research community. However, most existing steganalysis methods assume that steganography methods are known in advance, which in practice is impractical. That is why, in this paper, we present three blind detection schemes suitable for steganography in low‐bit‐rate speech streams. The first is based on mixed sample data augmentation. It randomly selects a certain proportion of steganographic samples from the sample set of each steganographic method to form a training set together with the original carrier samples for training to enhance the robustness of the model. The second relies on decision fusion where first step is to train a dedicated classification model for each steganography method and then use a majority voting mechanism in the detection stage to fuse the outputs of each model to give the final detection result. Compared to the other two steganalysis schemes, the third one design the detection model based on self‐paced ensemble according to the distribution characteristics of speech samples. Its main idea is to fully train multiple base classifiers through multiple iterations as well as under‐sampling processes, and organically fuse them to form a powerful ensemble classifier. In each iteration, differing from the traditional ensemble classifier solution, we put more attention to the steganographic samples at the decision boundary for the under‐sampling process of the steganography set composed of multiple steganography methods, rather than randomly selecting steganographic samples. The steganographic samples at the decision boundary are searched using the classification hardness given by the ensemble classifier trained in the last iteration, which is more informative and more conducive to improve the performance of base classifiers. The experimental results show that the proposed three schemes can achieve efficient blind detection for low‐bit‐rate speech‐based steganography, and the steganalysis scheme based on the self‐paced ensemble has the best performance. Specifically, when the embedding rate is at 30%, the accuracy of the steganalysis scheme based on self‐paced ensemble is more than 85%, while the accuracy of the other two steganalysis method is less than 80%. Additionally, the steganalysis scheme based on the self‐paced ensemble learning even outperforms dedicated detectors for specific steganographic methods in terms of recall for steganographic sample detection.

show abstract

“…To achieve fast and accurate detection of VoIP steganographic voice streams, Yang et al [84] proposed a fast steganalysis algorithm in 2020. First, the vector quantization codeword is mapped to a semantic space, and then a hidden layer is used to extract the relevant features of the codeword, which is then input into the softmax classifier.…”

Section: Steganalysis Based On Lpcmentioning

confidence: 99%

Steganography and Steganalysis in Voice over IP: A Review

Guo

Zhang

et al. 2021

Sensors

View full text Add to dashboard Cite

The rapid advance and popularization of VoIP (Voice over IP) has also brought security issues. VoIP-based secure voice communication has two sides: first, for legitimate users, the secret voice can be embedded in the carrier and transmitted safely in the channel to prevent privacy leakage and ensure data security; second, for illegal users, the use of VoIP Voice communication hides and transmits illegal information, leading to security incidents. Therefore, in recent years, steganography and steganography analysis based on VoIP have gradually become research hotspots in the field of information security. Steganography and steganalysis based on VoIP can be divided into two categories, depending on where the secret information is embedded: steganography and steganalysis based on voice payload or protocol. The former mainly regards voice payload as the carrier, and steganography or steganalysis is performed with respect to the payload. It can be subdivided into steganography and steganalysis based on FBC (fixed codebook), LPC (linear prediction coefficient), and ACB (adaptive codebook). The latter uses various protocols as the carrier and performs steganography or steganalysis with respect to some fields of the protocol header and the timing of the voice packet. It can be divided into steganography and steganalysis based on the network layer, the transport layer, and the application layer. Recent research results of steganography and steganalysis based on protocol and voice payload are classified in this paper, and the paper also summarizes their characteristics, advantages, and disadvantages. The development direction of future research is analyzed. Therefore, this research can provide good help and guidance for researchers in related fields.

show abstract

Fast Steganalysis Method for VoIP Streams

Cited by 18 publications

References 16 publications

Steganalysis of Compressed Speech Based on Global and Local Correlation Mining

Steganalysis of Compressed Speech Based on Global and Local Correlation Mining

Towards blind detection of steganography in low‐bit‐rate speech streams

Steganography and Steganalysis in Voice over IP: A Review

Contact Info

Product

Resources

About