Zhenyan Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhenyan Liu has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Jingfeng Xue
Beijing Institute of Technology, Beijing, China
10 shared publications - Yong Wang
Beijing Institute of Technology
8 shared publications - Xiaolin Zhao
Beijing Institute of Technology, Beijing, China
4 shared publications Ji Zhang
Beijing Institute of Technology
2 shared publicationsPengfei Zhang
Beijing Key Laboratory of Software Security Engineering Technology, School of Software, Beijing Institute of Technology, Beijing 100081, China
2 shared publicationsYifei Zeng
Beijing Key Laboratory of Software Security Engineering Technology, School of Software, Beijing Institute of Technology, Beijing 100081, China
2 shared publications
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6729-6743
PSDissect: A CFG-Guided, Semantics-Preserving Interactive Deobfuscation Framework for PowerShell Scripts
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6729-6743
Open AccessPSDissect: A CFG-Guided, Semantics-Preserving Interactive Deobfuscation Framework for PowerShell Scripts
- Open Access
- 26 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 834-843
OLG-FL: A Federated Learning Framework for Optimizing Local Training and Global Aggregation
- 26 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 834-843
Open AccessOLG-FL: A Federated Learning Framework for Optimizing Local Training and Global Aggregation
- Open Access
- 12 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 394-402
IFAA: An Improved Field Anonymity Algorithm for Efficient Big Data Privacy Preservation
- 12 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 394-402
Open AccessIFAA: An Improved Field Anonymity Algorithm for Efficient Big Data Privacy Preservation
- Open Access
- 12 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1771-1778
Analysis of optimal privacy protection mechanism based on IT-MPD
- 12 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1771-1778
Open AccessAnalysis of optimal privacy protection mechanism based on IT-MPD
- Open Access
- 11 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 41-51
RL4Mal: Representation learning-based malware classification under long-tailed distribution
- 11 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 41-51
Open AccessRL4Mal: Representation learning-based malware classification under long-tailed distribution
- Open Access
Classifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Drift
Data heterogeneity is one of the key challenges in federated learning, and many efforts have been devoted to tackling this problem. However, distributed concept drift with data heterogeneity, where clients may additionally experience different concept drifts, is a largely unexplored area. In this work, we focus on real drift, where the conditional distribution $P(Y|X)$ changes. We first study how distributed concept drift affects the model training and find that local classifier plays a critical role in drift adaptation. Moreover, to address data heterogeneity, we study the feature alignment under distributed concept drift, and find two factors that are crucial for feature alignment: the conditional distribution $P(Y|X)$ and the degree of data heterogeneity. Motivated by the above findings, we propose FedCCFA, a federated learning framework with classifier clustering and feature alignment. To enhance collaboration under distributed concept drift, FedCCFA clusters local classifiers at class-level and generates clustered feature anchors according to the clustering results. Assisted by these anchors, FedCCFA adaptively aligns clients' feature spaces based on the entropy of label distribution $P(Y)$, alleviating the inconsistency in feature space. Our results demonstrate that FedCCFA significantly outperforms existing methods under various concept drift settings. Code is available at https://github.com/Chen-Junbao/FedCCFA.Open AccessClassifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Drift
Data heterogeneity is one of the key challenges in federated learning, and many efforts have been devoted to tackling this problem. However, distributed concept drift with data heterogeneity, where clients may additionally experience different concept drifts, is a largely unexplored area. In this work, we focus on real drift, where the conditional distribution $P(Y|X)$ changes. We first study how distributed concept drift affects the model training and find that local classifier plays a critical role in drift adaptation. Moreover, to address data heterogeneity, we study the feature alignment under distributed concept drift, and find two factors that are crucial for feature alignment: the conditional distribution $P(Y|X)$ and the degree of data heterogeneity. Motivated by the above findings, we propose FedCCFA, a federated learning framework with classifier clustering and feature alignment. To enhance collaboration under distributed concept drift, FedCCFA clusters local classifiers at class-level and generates clustered feature anchors according to the clustering results. Assisted by these anchors, FedCCFA adaptively aligns clients' feature spaces based on the entropy of label distribution $P(Y)$, alleviating the inconsistency in feature space. Our results demonstrate that FedCCFA significantly outperforms existing methods under various concept drift settings. Code is available at https://github.com/Chen-Junbao/FedCCFA. - 24 June 2024
- Published by Springer Nature
- p. 29-42
LM-cAPI:A Lite Model Based on API Core Semantic Information for Malware Classification
- 24 June 2024
- Published by Springer Nature
- p. 29-42
LM-cAPI:A Lite Model Based on API Core Semantic Information for Malware Classification
- Open Access
- 10 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 285-291
GUCN: A machine learning model combining time series features for malicious network behavior detection
Malicious network behaviors significantly impact network and information security, the intelligent detection of network malicious behavior is an important work in the field of information and privacy protection. Traditional machine learning methods have achieved certain results in solving this problem, but generally ignore the continuous characteristics of malicious network behavior in time series. Aiming at this weakness, this paper proposes a Gated Unit Convolutional Networks (GUCN) model based on gated recurrent unit and convolutional neural network. Meanwhile, it also uses the feature screening method of random forest and the data dimension reduction method of UMAP to process the high dimensional data, which reduces the data redundancy. The results show that the method can effectively detect malicious network behavior, and because it can learn the objective characteristics of behavior in time series, it has the potential to identify malicious attack behavior in advance.
- 10 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 285-291
Open AccessGUCN: A machine learning model combining time series features for malicious network behavior detection
Malicious network behaviors significantly impact network and information security, the intelligent detection of network malicious behavior is an important work in the field of information and privacy protection. Traditional machine learning methods have achieved certain results in solving this problem, but generally ignore the continuous characteristics of malicious network behavior in time series. Aiming at this weakness, this paper proposes a Gated Unit Convolutional Networks (GUCN) model based on gated recurrent unit and convolutional neural network. Meanwhile, it also uses the feature screening method of random forest and the data dimension reduction method of UMAP to process the high dimensional data, which reduces the data redundancy. The results show that the method can effectively detect malicious network behavior, and because it can learn the objective characteristics of behavior in time series, it has the potential to identify malicious attack behavior in advance.
- 1 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Chinese Journal of Electronics
- Vol. 33 (1) , 128-138
Fast Cross-Platform Binary Code Similarity Detection Framework Based on CFGs Taking Advantage of NLP and Inductive GNN
Cross-platform binary code similarity detection aims at detecting whether two or more pieces of binary code are similar or not. Existing approaches that combine control flow graphs (CFGs)-based function representation and graph convolutional network (GCN)-based similarity analysis are the best-performing ones. Due to a large amount of convolutional computation and the loss of structural information, the use of convolution networks will inevitably bring problems such as high overhead and sometimes inaccuracy. To address these issues, we propose a fast cross-platform binary code similarity detection framework that takes advantage of natural language processing (NLP) and inductive graph neural network (GNN) for basic blocks embedding and function representation respectively by simulating extracting structural features and temporal features. GNN's node-centric and small batch is a suitable training way for large CFGs, it can greatly reduce computational overhead. Various NLP basic block embedding models and GNNs are evaluated. Experimental results show that the scheme with long short term memory (LSTM) for basic blocks embedding and inductive learning-based GraphSAGE(GAE) for function representation outperforms the state-of-the-art works. In our framework, we can take only 45% overhead. Improve efficiency significantly with a small performance trade-off.
- 1 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Chinese Journal of Electronics
- Vol. 33 (1) , 128-138
Fast Cross-Platform Binary Code Similarity Detection Framework Based on CFGs Taking Advantage of NLP and Inductive GNN
Cross-platform binary code similarity detection aims at detecting whether two or more pieces of binary code are similar or not. Existing approaches that combine control flow graphs (CFGs)-based function representation and graph convolutional network (GCN)-based similarity analysis are the best-performing ones. Due to a large amount of convolutional computation and the loss of structural information, the use of convolution networks will inevitably bring problems such as high overhead and sometimes inaccuracy. To address these issues, we propose a fast cross-platform binary code similarity detection framework that takes advantage of natural language processing (NLP) and inductive graph neural network (GNN) for basic blocks embedding and function representation respectively by simulating extracting structural features and temporal features. GNN's node-centric and small batch is a suitable training way for large CFGs, it can greatly reduce computational overhead. Various NLP basic block embedding models and GNNs are evaluated. Experimental results show that the scheme with long short term memory (LSTM) for basic blocks embedding and inductive learning-based GraphSAGE(GAE) for function representation outperforms the state-of-the-art works. In our framework, we can take only 45% overhead. Improve efficiency significantly with a small performance trade-off.
- 28 July 2023
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 77
WHGDroid: Effective android malware detection based on weighted heterogeneous graph
- 28 July 2023
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 77
WHGDroid: Effective android malware detection based on weighted heterogeneous graph