Binhui Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Binhui Tang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Caiyun Li3 shared publications
- Xiaowen Liu
College of Information Science and Technology, Hainan Normal University, Haikou, Hainan, China
3 shared publications Bo Dai
2 shared publicationsJie Ling
2 shared publicationsJunfeng Wang
2 shared publications- Wenhan Ge
College of Computer Science, Sichuan University, Chengdu, China
2 shared publications
Latest Publications
- 3 November 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 131
DepMIL-Net: Prototype-guided multiple instance learning for facial video-based depression severity estimation
- 3 November 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 131
DepMIL-Net: Prototype-guided multiple instance learning for facial video-based depression severity estimation
- 24 September 2026
- Published by Elsevier in Computer Networks
- Vol. 290
SEDetector: Privacy-preserving APT detection for CII via semantic evidence units and hypergraph learning
- 24 September 2026
- Published by Elsevier in Computer Networks
- Vol. 290
SEDetector: Privacy-preserving APT detection for CII via semantic evidence units and hypergraph learning
- 4 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 3829-3843
MetaCluster: A Universal Interpretable Classification Framework for Cybersecurity
Rising cyber threats have created an immediate demand for Deep Learning (DL) in cybersecurity. Nevertheless, the opaque nature of DL models poses challenges in deploying, collaborating, and assessing their effectiveness in less reliable cybersecurity environments. Despite eXplainable Artificial Intelligence (XAI) playing a role in enhancing cybersecurity analytics, the limited task scope, the propensity for data overfitting, and the stochastic explanations hinder its broader application. To fill the gap, this paper introduces a generic interpretable classification framework, named MetaCluster. MetaCluster generates semantic prototypes for features, patterns, and domains at varying granular levels by following three fundamental steps: embedding representations, acquiring prototypes, and aggregating semantics. These mechanisms guarantee that MetaCluster achieves critical information extraction and reliable classification at minimal cost. The experiments encompass cybersecurity classification tasks and assess the interpretability of the framework. These tasks encompass malware family classification, threat behavior analysis, and malicious traffic identification. In particular, when compared to other DL models, MetaCluster exhibits a significant reduction in parameter consumption by 79.52% to 91.78%, and boosts operational speed up to 71.37%, while its F1 scores remain stable or slightly increase. Additionally, MetaCluster possesses the ability to assess and visually represent the significance of image, text, and statistical features. This capability leads to a reduction of Mean Squared Error (MSE) between expected and actual predictions by 0.0101 to 0.1020.
- 4 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 3829-3843
MetaCluster: A Universal Interpretable Classification Framework for Cybersecurity
Rising cyber threats have created an immediate demand for Deep Learning (DL) in cybersecurity. Nevertheless, the opaque nature of DL models poses challenges in deploying, collaborating, and assessing their effectiveness in less reliable cybersecurity environments. Despite eXplainable Artificial Intelligence (XAI) playing a role in enhancing cybersecurity analytics, the limited task scope, the propensity for data overfitting, and the stochastic explanations hinder its broader application. To fill the gap, this paper introduces a generic interpretable classification framework, named MetaCluster. MetaCluster generates semantic prototypes for features, patterns, and domains at varying granular levels by following three fundamental steps: embedding representations, acquiring prototypes, and aggregating semantics. These mechanisms guarantee that MetaCluster achieves critical information extraction and reliable classification at minimal cost. The experiments encompass cybersecurity classification tasks and assess the interpretability of the framework. These tasks encompass malware family classification, threat behavior analysis, and malicious traffic identification. In particular, when compared to other DL models, MetaCluster exhibits a significant reduction in parameter consumption by 79.52% to 91.78%, and boosts operational speed up to 71.37%, while its F1 scores remain stable or slightly increase. Additionally, MetaCluster possesses the ability to assess and visually represent the significance of image, text, and statistical features. This capability leads to a reduction of Mean Squared Error (MSE) between expected and actual predictions by 0.0101 to 0.1020.
- 24 October 2023
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 112
STIOCS: Active learning-based semi-supervised training framework for IOC extraction
- 24 October 2023
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 112
STIOCS: Active learning-based semi-supervised training framework for IOC extraction
- 7 August 2023
- Published by Wiley in Transactions on Emerging Telecommunications Technologies
- Vol. 34 (11)
MUDROID: Android malware detection and classification based on permission and behavior for autonomous vehicles
With the growing popularity of autonomous vehicles, ensuring their safety has become a significant concern. Vehicle manufacturers have incorporated the Android operating system to enhance user convenience. However, the Android operating system's diversity and vulnerability may significantly impact autonomous vehicles because these natures lead to a critical threat in autonomous vehicle security: Android malware. The complex nature of multi‐data sources fusion in autonomous driving systems has resulted in low detection efficiency and accuracy for Android malware. Given the security requirements for autonomous‐driving systems, this article presents an Android malware classification method centered around the multifeature fusion and deep learning architecture designed to detect and classify Android malware within autonomous‐driving systems. The proposed MUDROID framework relies on the Android permission mechanism and behavioral feature to formulate a malware classification model. Comprising four essential components—feature extraction, representation, multifeature fusion, and classifier training, MUDROID leverages the advantages of CNN and GCN combination model and is adept at extracting and interpreting multidimensional features, consequently constructing a multifeature fusion classifier to amplify the efficiency and accuracy of Android malware detection and classification. The experiment results support MUDROID's superior classification performance, with an impressive Android malware detection accuracy rate of 98.69% and family classification (95.42%). The proposed method can detect and classify Android malware effectively, thus elevating the security and robustness of the self‐driving system. Additionally, the approach in this article also addresses feature representation issues in detecting malware variants, facilitating the recognition of Android malware variants across diverse platforms.
- 7 August 2023
- Published by Wiley in Transactions on Emerging Telecommunications Technologies
- Vol. 34 (11)
MUDROID: Android malware detection and classification based on permission and behavior for autonomous vehicles
With the growing popularity of autonomous vehicles, ensuring their safety has become a significant concern. Vehicle manufacturers have incorporated the Android operating system to enhance user convenience. However, the Android operating system's diversity and vulnerability may significantly impact autonomous vehicles because these natures lead to a critical threat in autonomous vehicle security: Android malware. The complex nature of multi‐data sources fusion in autonomous driving systems has resulted in low detection efficiency and accuracy for Android malware. Given the security requirements for autonomous‐driving systems, this article presents an Android malware classification method centered around the multifeature fusion and deep learning architecture designed to detect and classify Android malware within autonomous‐driving systems. The proposed MUDROID framework relies on the Android permission mechanism and behavioral feature to formulate a malware classification model. Comprising four essential components—feature extraction, representation, multifeature fusion, and classifier training, MUDROID leverages the advantages of CNN and GCN combination model and is adept at extracting and interpreting multidimensional features, consequently constructing a multifeature fusion classifier to amplify the efficiency and accuracy of Android malware detection and classification. The experiment results support MUDROID's superior classification performance, with an impressive Android malware detection accuracy rate of 98.69% and family classification (95.42%). The proposed method can detect and classify Android malware effectively, thus elevating the security and robustness of the self‐driving system. Additionally, the approach in this article also addresses feature representation issues in detecting malware variants, facilitating the recognition of Android malware variants across diverse platforms.
- Open Access
- 17 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 576-583
APT Detector: Detect and Identify APT Malware Based on Deep Learning Framework
Advanced persistent threat (APT) attacks use sophisticated attack techniques and covert command and control (C&C) channels to conduct long-term sustained cyber attacks on specific targets as unobtrusively as possible. Over the past ten years, APT attacks have become increasingly frequent, gradually taking on a highly organized, nationalized, and militarized nature. Because APT malware is highly covert, has a long latency period, and presents characteristics such as diversification, high frequency, and sophistication. In the face of existing detection methods, it is easy for attackers to bypass detection by customizing malware and adapting and configuring tools to the target network. The continuous improvement of network technologies and tools and the complex and diverse attack process make it very difficult to detect unknown APT malware. To address the problems, this paper takes APT malware as the detection object and collects 6777 malware from 20 types of APT attack actors. Through the improved Convolutional Neural network (CNN) model combined with an attention mechanism to complete automatic extraction and weighting of static malware features, which can detect and discover APT malware. Meanwhile, the recognition effect for APT malware is better than other existing methods, which realize the attribution of APT attack groups.
- 17 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 576-583
Open AccessAPT Detector: Detect and Identify APT Malware Based on Deep Learning Framework
Advanced persistent threat (APT) attacks use sophisticated attack techniques and covert command and control (C&C) channels to conduct long-term sustained cyber attacks on specific targets as unobtrusively as possible. Over the past ten years, APT attacks have become increasingly frequent, gradually taking on a highly organized, nationalized, and militarized nature. Because APT malware is highly covert, has a long latency period, and presents characteristics such as diversification, high frequency, and sophistication. In the face of existing detection methods, it is easy for attackers to bypass detection by customizing malware and adapting and configuring tools to the target network. The continuous improvement of network technologies and tools and the complex and diverse attack process make it very difficult to detect unknown APT malware. To address the problems, this paper takes APT malware as the detection object and collects 6777 malware from 20 types of APT attack actors. Through the improved Convolutional Neural network (CNN) model combined with an attention mechanism to complete automatic extraction and weighting of static malware features, which can detect and discover APT malware. Meanwhile, the recognition effect for APT malware is better than other existing methods, which realize the attribution of APT attack groups.