Zhongliang Yang

Zhongliang Yang

Auto-generated profile, based on publicly available information

Zhongliang Yang

Beijing University of Posts and Telecommunications

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 September 2018 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
ZYZhong-Liang Yang
Zhong-Liang Yang
XGXiaoqing Guo
Xiaoqing Guo
ZCZi-Ming Chen
Zi-Ming Chen
YHYongfeng HUANG
Yongfeng HUANG
YZYu-Jin Zhang
Yu-Jin Zhang
Linguistic steganography based on text carrier autogeneration technology is a current topic with great promise and unpredictable challenges. Limited by the text automatic generation technology or the corresponding text coding methods, the quality of the steganographic text generated by previous methods is inferior, which makes its imperceptibility unsatisfactory. In this paper, we propose a linguistic steganography based on Recurrent Neural Networks (RNN-Stega), which can automatically generate high-quality text covers on the basis of a secret bitstream that needs to be embedded. We trained our model with a large number of artificially generated samples and obtained a good estimate of the statistical language model. In the text generation process, we propose Fixed-Length Coding (FLC) and Variable-Length Coding (VLC) to encode words based on their conditional probability distribution. We designed several experiments to test the proposed model from the perspectives of information embedding efficiency, information imperceptibility and information hidden capacity. Experimental results show that the proposed model outperforms all the previous related methods and achieves the state of the art performance.

10 September 2020 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
ZYZhong-Liang Yang
Zhong-Liang Yang
SZSi-Yu Zhang
Si-Yu Zhang
YHYu-Ting Hu
Yu-Ting Hu
ZHZhiwen Hu
Zhiwen Hu
YHYongfeng HUANG
Yongfeng HUANG
In recent years, linguistic steganography based on text auto-generation technology has been greatly developed, which is considered to be a very promising but also a very challenging research topic. Previous works mainly focus on optimizing the language model and conditional probability coding methods, aiming at generating steganographic sentences with better quality. In this paper, we first report some of our latest experimental findings, which seem to indicate that the quality of the generated steganographic text cannot fully guarantee its steganographic security, and even has a prominent perceptualimperceptibility and statistical-imperceptibility conflict (Psic) effect. To further improve the imperceptibility and security of generated steganographic texts, in this paper, we propose a new linguistic steganography based on Variational Auto- Encoder (VAE), which can be called VAE-Stega. We use the encoder in VAE-Stega to learn the overall statistical distribution characteristics of a large number of normal texts, and then use the decoder in VAE-Stega to generate steganographic sentences which conform to both of the statistical language model as well as the overall statistical distribution of normal sentences, so as to guarantee both the perceptual-imperceptibility and statisticalimperceptibility of the generated steganographic texts at the same time. We design several experiments to test the proposed method. Experimental results show that the proposed model can greatly improve the imperceptibility of the generated steganographic sentences when comparing with the previous methods, which achieves the state of the art performance.

3 June 2019 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
ZYZhongliang Yang
Zhongliang Yang
KWKe Wang
Ke Wang
JLJian Li
Jian Li
YHYongfeng HUANG
Yongfeng HUANG
YZYu-Jin Zhang
Yu-Jin Zhang
With the rapid development of natural language processing technologies, more and more text steganographic methods based on automatic text generation technology have appeared in recent years. These models use the powerful self-learning and feature extraction ability of the neural networks to learn the feature expression of massive normal texts. Then they can automatically generate dense steganographic texts which conform to such statistical distribution based on the learned statistical patterns. In this paper, we observe that the conditional probability distribution of each word in the automatically generated steganographic texts will be distorted after embedded with hidden information. We use Recurrent Neural Networks (RNNs) to extract these feature distribution differences and then classify those features into cover text and stego text categories. Experimental results show that the proposed model can achieve high detection accuracy. Besides, the proposed model can even make use of the subtle differences of the feature distribution of texts to estimate the amount of hidden information embedded in the generated steganographic text.

27 February 2019 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
ZYZhongliang Yang
Zhongliang Yang
YHYongfeng HUANG
Yongfeng HUANG
YZYu-Jin Zhang
Yu-Jin Zhang
With the rapid development of natural language processing (NLP) technology in the past few years, the steganography by text synthesis has been greatly developed. These methods can analyze the statistical feature distribution of a large number of training samples, and then generate steganographic texts that conform to such statistical distribution. For these steganography methods, previous steganalysis methods show unsatisfactory detection performance, which remains an unsolved problem and poses a great threat to the security of cyberspace. In this paper, we propose a fast and efficient text steganalysis method to solve this problem. We first analyzed the correlation between words in these generated steganographic texts. Then we map each word to a semantic space and use a hidden layer to extract the correlations between these words. Finally, based on the extracted correlation features, we use the softmax classifier to classify the input text. Experiment results show that the proposed model can achieve a high detection accuracy, which shows a state-of-the-art performance.

16 November 2020 in Journal of Medical Internet Research
Verified
Journal Article
Open access
ZHZhiwen Hu
Zhiwen Hu
ZYZhongliang Yang
Zhongliang Yang
QLQi Li
Qi Li
An ZhangAn Zhang
An Zhang
Background: In the context of the COVID-19 infodemic, the global profusion of monikers and hashtags for COVID-19 have found their way into daily communication and contributed to a backlash against China and the Chinese people. Objective: This study examines public engagement in crisis communication about COVID-19 during the early epidemic stage and the practical strategy of social mobilization to mitigate the infodemic. Methods: We retrieved the unbiased values of the top-ranked search phrases between December 30, 2019, and July 15, 2020, which normalized the anonymized, categorized, and aggregated samples from Google Search data. This study illustrates the most-searched terms, including the official COVID-19 terms, the stigmatized terms, and other controls, to measure the collective behavioral propensities to stigmatized terms and to explore the global reaction to the COVID-19 epidemic in the real world. We calculated the ratio of the cumulative number of COVID-19 cases to the regional population as the cumulative rate (R) of a specific country or territory and calculated the Gini coefficient (G) to measure the collective heterogeneity of crowd behavior. Results: People around the world are using stigmatizing terms on Google Search, and these terms were used earlier than the official names. Many stigmatized monikers against China (eg, “Wuhan pneumonia,” G=0.73; “Wuhan coronavirus,” G=0.60; “China pneumonia,” G=0.59; “China coronavirus,” G=0.52; “Chinese coronavirus,” G=0.50) had high collective heterogeneity of crowd behavior between December 30, 2019, and July 15, 2020, while the official terms “COVID-19” (G=0.44) and “SARS-CoV-2” (G=0.42) have not become de facto standard usages. Moreover, the pattern of high consistent usage was observed in 13 territories with low cumulative rates (R) between January 16 and July 15, 2020, out of 58 countries and territories that have reported confirmed cases of COVID-19. In the scientific literature, multifarious naming practices may have provoked unintended negative impacts by stigmatizing Chinese people. The World Health Organization; the United Nations Educational, Scientific and Cultural Organization; and the media initiated campaigns for fighting back against the COVID-19 infodemic with the same mission but in diverse voices. Conclusions: Infodemiological analysis can articulate the collective propensities to stigmatized monikers across search behaviors, which may reflect the collective sentiment of backlash against China and Chinese people in the real world. The full-fledged official terms are expected to fight back against the resilience of negative perceptual bias amid the COVID-19 epidemic. Such official naming efforts against the infodemic should be met with a fair share of identification in scientific conventions and sociocultural paradigms. As an integral component of preparedness, appropriate nomenclatures should be duly assigned to the newly identified coronavirus, and social mobilization in a uniform voice is a priority for combating the next infodemic.

2 March 2020 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
ZYZhongliang Yang
Zhongliang Yang
YHYongfeng Huang
Yongfeng Huang
YZYu-Jin Zhang
Yu-Jin Zhang