Chengzhang Zhu

Chengzhang Zhu


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
11 September 2020 in Mathematics
Verified
Journal Article
Open access
PDF file
LXLingyun Xiang
Lingyun Xiang
SYShuanghui Yang
Shuanghui Yang
YLYuhang Liu
Yuhang Liu
QLQian Li
Qian Li
CZChengzhang Zhu
Chengzhang Zhu
With the development of natural language processing, linguistic steganography has become a research hotspot in the field of information security. However, most existing linguistic steganographic methods may suffer from the low embedding capacity problem. Therefore, this paper proposes a character-level linguistic steganographic method (CLLS) to embed the secret information into characters instead of words by employing a long short-term memory (LSTM) based language model. First, the proposed method utilizes the LSTM model and large-scale corpus to construct and train a character-level text generation model. Through training, the best evaluated model is obtained as the prediction model of generating stego text. Then, we use the secret information as the control information to select the right character from predictions of the trained character-level text generation model. Thus, the secret information is hidden in the generated text as the predicted characters having different prediction probability values can be encoded into different secret bit values. For the same secret information, the generated stego texts vary with the starting strings of the text generation model, so we design a selection strategy to find the highest quality stego text from a number of candidate stego texts as the final stego text by changing the starting strings. The experimental results demonstrate that compared with other similar methods, the proposed method has the fastest running speed and highest embedding capacity. Moreover, extensive experiments are conducted to verify the effect of the number of candidate stego texts on the quality of the final stego text. The experimental results show that the quality of the final stego text increases with the number of candidate stego texts increasing, but the growth rate of the quality will slow down.

21 July 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
CZChengzhang Zhu
Chengzhang Zhu
LCLongbing Cao
Longbing Cao
JYJianping Yin
Jianping Yin
Complex categorical data is often hierarchically coupled with heterogeneous relationships between attributes and attribute values and the couplings between objects. Such value-to-object couplings are heterogeneous with complementary and inconsistent interactions and distributions. Limited research exists on unlabeled categorical data representations, ignores the heterogeneous and hierarchical couplings, underestimates data characteristics and complexities, and overuses redundant information, etc. Deep representation learning of unlabeled categorical data is challenging, overseeing such value-to-object couplings, complementarity and inconsistency, and requiring large data, disentanglement, and high computational power. This work introduces a shallow but powerful UNsupervised heTerogeneous couplIng lEarning (UNTIE) approach for representing coupled categorical data by untying the interactions between couplings and revealing heterogeneous distributions embedded in each type of couplings. UNTIE is efficiently optimized w.r.t. a kernel k-means objective function for unsupervised representation learning of heterogeneous and hierarchical value-to-object couplings. Theoretical analysis shows that UNTIE can represent categorical data with maximal separability while effectively represents heterogeneous couplings and disclose their roles in categorical data. The UNTIE-learned representations make significant performance improvement against the state-of-the-art categorical representations and deep representation models on 25 categorical data sets with diversified characteristics.

9 January 2018 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
CZChengzhang Zhu
Chengzhang Zhu
LCLongbing Cao
Longbing Cao
QLQiang Liu
Qiang Liu
JYJianping Yin
Jianping Yin
Vipin KumarVipin Kumar
Vipin Kumar
Learning appropriate metric is critical for effectively capturing complex data characteristics. The metric learning of categorical data with hierarchical coupling relationships and local heterogeneous distributions is very challenging yet rarely explored. This paper proposes a Heterogeneous mEtric Learning with hIerarchical Couplings, HELIC, for this type of categorical data. HELIC captures both low-level value-to-attribute and high-level attribute-to-class hierarchical couplings, and reveals the intrinsic heterogeneities embedded in each level of couplings. Theoretical analyses of the effectiveness and generalization error bound verify that HELIC effectively represents the above complexities. Extensive experiments on 30 data sets with diverse characteristics demonstrate that HELIC-enabled classification significantly enhances the accuracy (up to 40.93%), compared with five state-of-the-art baselines.

1 January 2020 in Intelligent Automation and Soft Computing
Verified
Journal Article
Open access
LXLingyun Xiang
Lingyun Xiang
GGGuoqing Guo
Guoqing Guo
QLQian Li
Qian Li
CZChengzhang Zhu
Chengzhang Zhu
JCJiuren Chen
Jiuren Chen
HMHaoliang Ma
Haoliang Ma
Current works on spam detection in product reviews tend to ignore the temporal relevance among reviews in the user or product entity, resulting in poor detection performance. To address this issue, the present paper proposes a spam detection method that jointly learns comprehensive temporal features from both behavioral and text features in user and product entities. We first extract the behavioral features of a single review, then employ a convolutional neural network (CNN) to learn the text features of this review. We next combine the behavioral features with the text features of each review and train a Long-Short-Term Memory (LSTM) model to learn the temporal features of every review in the user and product entities. Finally, we train a classifier using all of the learned temporal features in order to predict whether a particular review is spam. Experimental results demonstrate that the proposed method can effectively extract the temporal features from historical activities, and can further jointly analyze the activity trajectories from multiple entities. Thus, the proposed method significantly improves the spam detection accuracy.

1 January 2016 in Neurocomputing
Verified
Journal Article
Closed access
QLQiang Liu
Qiang Liu
SZSihang Zhou
Sihang Zhou
CZChengzhang Zhu
Chengzhang Zhu
XLXinwang Liu
Xinwang Liu
JYJianping Yin
Jianping Yin

1 July 2014
Verified
Conference Paper
Closed access
SZSihang Zhou
Sihang Zhou
XLXinwang Liu
Xinwang Liu
CZChengzhang Zhu
Chengzhang Zhu
QLQiang Liu
Qiang Liu
JYJianping Yin
Jianping Yin
In this paper, we propose an unsupervised feature selection framework which simultaneously preserves the local geometric structure and global discriminative structure of data. Also, the spectral clustering algorithm is incorporated into this framework to exploit the discriminative structure. To demonstrate the generality of our framework, we instantiate our framework into two specific algorithms by characterizing the local geometric structure of data with two well-known models, i.e., locally linear embedding and linear preserve projection. After that, we provide an efficient algorithm with proved convergence to solve the resultant optimization problem. Comprehensive experiments have been conducted on eleven benchmark data sets and the results demonstrate the superior performance of our framework.