Jun Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jun Zhang has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Yonghang Tai
Yunnan Normal University
6 shared publications Guanjun Lin
School of Information Engineering, Sanming University, Sanming, Fujian 365004, China
2 shared publicationsZhibao Qin
School of Physics and Electronic Information, Yunnan Normal University, Kunming 650500, China
2 shared publicationsBixuan Gao
Yunnan Key Laboratory of Opto-Electronic Information Technology, Yunnan Normal University, Kunming 650000, China
1 shared publication- Bonan Zhang
City University of Macau
1 shared publication - Chao Chen
RMIT University
1 shared publication
Latest Publications
- Open Access
- 25 October 2023
- Published by Wiley in Security and Communication Networks
- Vol. 2023, 1-10
Deep Graph Embedding for IoT Botnet Traffic Detection
Botnet attacks have mainly targeted computers in the past, which is a fundamental cybersecurity problem. Due to the booming of Internet of things (IoT) devices, an increasing number of botnet attacks are now targeting IoT devices. Researchers have proposed several mechanisms to avoid botnet attacks, such as identification by communication patterns or network topology and defence by DNS blacklisting. A popular direction for botnet detection currently relies on the specific topological characteristics of botnets and uses machine learning models. However, it relies on network experts’ domain knowledge for feature engineering. Recently, neural networks have shown the capability of representation learning. This paper proposes a new approach to extracting graph features via graph neural networks. To capture the particular topology of the botnet, we transform the network traffic into graphs and train a graph neural network to extract features. In our evaluations, we use graph embedding features to train six machine learning models and compare them with the performance of traditional graph features in identifying botnet nodes. The experimental results show that botnet traffic detection is still challenging even with neural networks. We should consider the impact of data, features, and algorithms for an accurate and robust solution.
- 25 October 2023
- Published by Wiley in Security and Communication Networks
- Vol. 2023, 1-10
Open AccessDeep Graph Embedding for IoT Botnet Traffic Detection
Botnet attacks have mainly targeted computers in the past, which is a fundamental cybersecurity problem. Due to the booming of Internet of things (IoT) devices, an increasing number of botnet attacks are now targeting IoT devices. Researchers have proposed several mechanisms to avoid botnet attacks, such as identification by communication patterns or network topology and defence by DNS blacklisting. A popular direction for botnet detection currently relies on the specific topological characteristics of botnets and uses machine learning models. However, it relies on network experts’ domain knowledge for feature engineering. Recently, neural networks have shown the capability of representation learning. This paper proposes a new approach to extracting graph features via graph neural networks. To capture the particular topology of the botnet, we transform the network traffic into graphs and train a graph neural network to extract features. In our evaluations, we use graph embedding features to train six machine learning models and compare them with the performance of traditional graph features in identifying botnet nodes. The experimental results show that botnet traffic detection is still challenging even with neural networks. We should consider the impact of data, features, and algorithms for an accurate and robust solution.
- Open Access
- 21 July 2023
- Published by Springer Nature in Research Square
Deep Learning-Based Noninvasive Auxiliary Pulmonary TumorDiagnosis System on Multi-modality Radio-mics Data
The increasing prevalence of lung cancer necessitates the development of non-invasive preliminaryscreening systems to support clinical diagnosis scenarios. Currently, the core challenges in noduledetection involve misalignment and data sparsity. Moreover, post-cancer screening, single modalityinformation is inadequate for comprehensive analysis of lung cancer by medical professionals. In thisarticle, we propose two methods for preliminary cancer screening and medical analysis, respectively.Firstly, we introduce a hybrid training strategy to optimize the TOOD architecture, addressing thechallenges encountered during the preliminary screening process. Secondly, we extract radiomicsfeatures from nodule images, adhering to the image biomarker standardization initiative (IBSI). Byconsidering radiomics characteristics as independent variables and effective survival prognosis asthe dependent variable, we explore the relationship between tumor images and survival prognosis.The proposed method demonstrates a reduction in TOOD detection speed from 4.4s to 3.3s, andimproved mAP50 and Recall values for the hybrid neural network (TOOD+DCNV) from 0.4871to 0.7123 and 0.6181 to 0.8325, respectively. Comprehensive validation supports the effectivenessof the proposed method for preliminary nodule detection. Furthermore, the proposed non-invasivepreliminary screening system yields 107 quantitative radiomics features from detected nodules, witha text classification accuracy of 72%. Overall, the integration of deep learning and multi-model dataforms the foundation of the preliminary screening system, offering potential to alleviate the burden oftumor diagnosis and achieve intelligent assistive medical capabilities.
- 21 July 2023
- Published by Springer Nature in Research Square
Open AccessDeep Learning-Based Noninvasive Auxiliary Pulmonary TumorDiagnosis System on Multi-modality Radio-mics Data
The increasing prevalence of lung cancer necessitates the development of non-invasive preliminaryscreening systems to support clinical diagnosis scenarios. Currently, the core challenges in noduledetection involve misalignment and data sparsity. Moreover, post-cancer screening, single modalityinformation is inadequate for comprehensive analysis of lung cancer by medical professionals. In thisarticle, we propose two methods for preliminary cancer screening and medical analysis, respectively.Firstly, we introduce a hybrid training strategy to optimize the TOOD architecture, addressing thechallenges encountered during the preliminary screening process. Secondly, we extract radiomicsfeatures from nodule images, adhering to the image biomarker standardization initiative (IBSI). Byconsidering radiomics characteristics as independent variables and effective survival prognosis asthe dependent variable, we explore the relationship between tumor images and survival prognosis.The proposed method demonstrates a reduction in TOOD detection speed from 4.4s to 3.3s, andimproved mAP50 and Recall values for the hybrid neural network (TOOD+DCNV) from 0.4871to 0.7123 and 0.6181 to 0.8325, respectively. Comprehensive validation supports the effectivenessof the proposed method for preliminary nodule detection. Furthermore, the proposed non-invasivepreliminary screening system yields 107 quantitative radiomics features from detected nodules, witha text classification accuracy of 72%. Overall, the integration of deep learning and multi-model dataforms the foundation of the preliminary screening system, offering potential to alleviate the burden oftumor diagnosis and achieve intelligent assistive medical capabilities.
- 14 March 2022
- Published by Wiley in International Journal of Network Management
- Vol. 33 (3)
Intelligent detection of vulnerable functions in software through neural embedding‐based code analysis
Summary: Software vulnerability is a fundamental problem in cybersecurity, which poses severe threats to the secure operation of devices and systems. In this paper, we propose a new vulnerability detection framework of employing advanced neural embedding. For example, CodeBERT is a large‐scale pre‐trained embedding model for natural language and programming language. It achieves state‐of‐the‐art performance on various natural language processing and code analysis tasks, demonstrating improved generalization ability compared with conventional models. The proposed framework encapsulates CodeBERT as a code representation generator and combines it with transfer learning to conduct cross‐project vulnerability detection. Considering the problem of lacking code embedding models on C source code, we extract the knowledge from C source code to fine‐tune the pre‐trained embedding model, so as to better facilitate the detection of function‐level vulnerabilities in C open‐source projects. To address the severe data imbalance issue in real‐world scenarios, we introduce code argumentation idea and use a large number of synthetic vulnerability data to further improve the robustness of the detection method. Experimental results show that the proposed vulnerability detection framework achieves better performance than existing methods.
- 14 March 2022
- Published by Wiley in International Journal of Network Management
- Vol. 33 (3)
Intelligent detection of vulnerable functions in software through neural embedding‐based code analysis
Summary: Software vulnerability is a fundamental problem in cybersecurity, which poses severe threats to the secure operation of devices and systems. In this paper, we propose a new vulnerability detection framework of employing advanced neural embedding. For example, CodeBERT is a large‐scale pre‐trained embedding model for natural language and programming language. It achieves state‐of‐the‐art performance on various natural language processing and code analysis tasks, demonstrating improved generalization ability compared with conventional models. The proposed framework encapsulates CodeBERT as a code representation generator and combines it with transfer learning to conduct cross‐project vulnerability detection. Considering the problem of lacking code embedding models on C source code, we extract the knowledge from C source code to fine‐tune the pre‐trained embedding model, so as to better facilitate the detection of function‐level vulnerabilities in C open‐source projects. To address the severe data imbalance issue in real‐world scenarios, we introduce code argumentation idea and use a large number of synthetic vulnerability data to further improve the robustness of the detection method. Experimental results show that the proposed vulnerability detection framework achieves better performance than existing methods.
- Open Access
- 18 January 2022
- Published by Wiley in Security and Communication Networks
- Vol. 2022, 1-12
Deep Neural Embedding for Software Vulnerability Discovery: Comparison and Optimization
Due to multitudinous vulnerabilities in sophisticated software programs, the detection performance of existing approaches requires further improvement. Multiple vulnerability detection approaches have been proposed to aid code inspection. Among them, there is a line of approaches that apply deep learning (DL) techniques and achieve promising results. This paper attempts to utilize CodeBERT which is a deep contextualized model as an embedding solution to facilitate the detection of vulnerabilities in C open-source projects. The application of CodeBERT for code analysis allows the rich and latent patterns within software code to be revealed, having the potential to facilitate various downstream tasks such as the detection of software vulnerability. CodeBERT inherits the architecture of BERT, providing a stacked encoder of transformer in a bidirectional structure. This facilitates the learning of vulnerable code patterns which requires long-range dependency analysis. Additionally, the multihead attention mechanism of transformer enables multiple key variables of a data flow to be focused, which is crucial for analyzing and tracing potentially vulnerable data flaws, eventually, resulting in optimized detection performance. To evaluate the effectiveness of the proposed CodeBERT-based embedding solution, four mainstream-embedding methods are compared for generating software code embeddings, including Word2Vec, GloVe, and FastText. Experimental results show that CodeBERT-based embedding outperforms other embedding models on the downstream vulnerability detection tasks. To further boost performance, we proposed to include synthetic vulnerable functions and perform synthetic and real-world data fine tuning to facilitate the model learning of C-related vulnerable code patterns. Meanwhile, we explored the suitable configuration of CodeBERT. The evaluation results show that the model with new parameters outperform some state-of-the-art detection methods in our dataset.
- 18 January 2022
- Published by Wiley in Security and Communication Networks
- Vol. 2022, 1-12
Open AccessDeep Neural Embedding for Software Vulnerability Discovery: Comparison and Optimization
Due to multitudinous vulnerabilities in sophisticated software programs, the detection performance of existing approaches requires further improvement. Multiple vulnerability detection approaches have been proposed to aid code inspection. Among them, there is a line of approaches that apply deep learning (DL) techniques and achieve promising results. This paper attempts to utilize CodeBERT which is a deep contextualized model as an embedding solution to facilitate the detection of vulnerabilities in C open-source projects. The application of CodeBERT for code analysis allows the rich and latent patterns within software code to be revealed, having the potential to facilitate various downstream tasks such as the detection of software vulnerability. CodeBERT inherits the architecture of BERT, providing a stacked encoder of transformer in a bidirectional structure. This facilitates the learning of vulnerable code patterns which requires long-range dependency analysis. Additionally, the multihead attention mechanism of transformer enables multiple key variables of a data flow to be focused, which is crucial for analyzing and tracing potentially vulnerable data flaws, eventually, resulting in optimized detection performance. To evaluate the effectiveness of the proposed CodeBERT-based embedding solution, four mainstream-embedding methods are compared for generating software code embeddings, including Word2Vec, GloVe, and FastText. Experimental results show that CodeBERT-based embedding outperforms other embedding models on the downstream vulnerability detection tasks. To further boost performance, we proposed to include synthetic vulnerable functions and perform synthetic and real-world data fine tuning to facilitate the model learning of C-related vulnerable code patterns. Meanwhile, we explored the suitable configuration of CodeBERT. The evaluation results show that the model with new parameters outperform some state-of-the-art detection methods in our dataset.
- Open Access
- 18 November 2021
- Published by Wiley in Security and Communication Networks
- Vol. 2021, 1-10
Image Speckle Denoising for Securing Internet of Smart Sensors
How to improve utility performance when securing sensitive data is an important research problem in Internet of smart sensors. In this paper, we study secured image speckle denoising for networked synthetic aperture radar (SAR). Speckle noise of SAR affects image quality and has a great influence on target detection and recognition. MSTAR dataset is often used in image target recognition. In this paper, a subregion-based method is proposed in order to improve the accuracy of target recognition and better retain target information while filtering and denoising the image. The new method applies advanced encryption techniques to protect sensitive data against malicious attack. Firstly, the image is divided into marked areas and unmarked areas through edge extraction and hole filling. Secondly, we use different size windows and filtering methods to filter the image in different areas. The experimental results show that the proposed algorithm has obvious advantages over MR-NLM, SSIM-NLM, Frost, and BM3D filtering in terms of equivalent view number and preserving edge and structure.
- 18 November 2021
- Published by Wiley in Security and Communication Networks
- Vol. 2021, 1-10
Open AccessImage Speckle Denoising for Securing Internet of Smart Sensors
How to improve utility performance when securing sensitive data is an important research problem in Internet of smart sensors. In this paper, we study secured image speckle denoising for networked synthetic aperture radar (SAR). Speckle noise of SAR affects image quality and has a great influence on target detection and recognition. MSTAR dataset is often used in image target recognition. In this paper, a subregion-based method is proposed in order to improve the accuracy of target recognition and better retain target information while filtering and denoising the image. The new method applies advanced encryption techniques to protect sensitive data against malicious attack. Firstly, the image is divided into marked areas and unmarked areas through edge extraction and hole filling. Secondly, we use different size windows and filtering methods to filter the image in different areas. The experimental results show that the proposed algorithm has obvious advantages over MR-NLM, SSIM-NLM, Frost, and BM3D filtering in terms of equivalent view number and preserving edge and structure.
- 19 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 17 (9) , 6519-6527
Intelligent Intraoperative Haptic-AR Navigation for COVID-19 Lung Biopsy Using Deep Hybrid Model
A novel intelligent navigation technique for accurate image-guided COVID-19 lung biopsy is addressed, which systematically combines augmented reality (AR), customized haptic-enabled surgical tools, and deep neural network to achieve customized surgical navigation. Clinic data from 341 COVID-19 positive patients, with 1598 negative control group, have collected for the model synergy and evaluation. Biomechanics force data from the experiment are applied a WPD-CNN-LSTM (WCL) to learn a new patient-specific COVID-19 surgical model, and the ResNet was employed for the intraoperative force classification. To boost the user immersion and promote the user experience, intro-operational guiding images have combined with the haptic-AR navigational view. Furthermore, a 3-D user interface (3DUI), including all requisite surgical details, was developed with a real-time response guaranteed. Twenty-four thoracic surgeons were invited to the objective and subjective experiments for performance evaluation. The root-mean-square error results of our proposed WCL model is 0.0128, and the classification accuracy is 97%, which demonstrated that the innovative AR with deep learning (DL) intelligent model outperforms the existing perception navigation techniques with significantly higher performance. This article shows a novel framework in the interventional surgical integration for COVID-19 and opens the new research about the integration of AR, haptic rendering, and deep learning for surgical navigation.
- 19 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 17 (9) , 6519-6527
Intelligent Intraoperative Haptic-AR Navigation for COVID-19 Lung Biopsy Using Deep Hybrid Model
A novel intelligent navigation technique for accurate image-guided COVID-19 lung biopsy is addressed, which systematically combines augmented reality (AR), customized haptic-enabled surgical tools, and deep neural network to achieve customized surgical navigation. Clinic data from 341 COVID-19 positive patients, with 1598 negative control group, have collected for the model synergy and evaluation. Biomechanics force data from the experiment are applied a WPD-CNN-LSTM (WCL) to learn a new patient-specific COVID-19 surgical model, and the ResNet was employed for the intraoperative force classification. To boost the user immersion and promote the user experience, intro-operational guiding images have combined with the haptic-AR navigational view. Furthermore, a 3-D user interface (3DUI), including all requisite surgical details, was developed with a real-time response guaranteed. Twenty-four thoracic surgeons were invited to the objective and subjective experiments for performance evaluation. The root-mean-square error results of our proposed WCL model is 0.0128, and the classification accuracy is 97%, which demonstrated that the innovative AR with deep learning (DL) intelligent model outperforms the existing perception navigation techniques with significantly higher performance. This article shows a novel framework in the interventional surgical integration for COVID-19 and opens the new research about the integration of AR, haptic rendering, and deep learning for surgical navigation.
- Open Access
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
Trustworthy Image Fusion with Deep Learning for Wireless Applications
To fuse infrared and visible images in wireless applications, the extraction and transmission of characteristic information security is an important task. The fused image quality depends on the effectiveness of feature extraction and the transmission of image pair characteristics. However, most fusion approaches based on deep learning do not make effective use of the features for image fusion, which results in missing semantic content in the fused image. In this paper, a novel trustworthy image fusion method is proposed to address these issues, which applies convolutional neural networks for feature extraction and blockchain technology to protect sensitive information. The new method can effectively reduce the loss of feature information by making the output of the feature extraction network in each convolutional layer to be fed to the next layer along with the production of the previous layer, and in order to ensure the similarity between the fused image and the original image, the original input image feature map is used as the input of the reconstruction network in the image reconstruction network. Compared to other methods, the experimental results show that our proposed method can achieve better quality and satisfy human perception.
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
Open AccessTrustworthy Image Fusion with Deep Learning for Wireless Applications
To fuse infrared and visible images in wireless applications, the extraction and transmission of characteristic information security is an important task. The fused image quality depends on the effectiveness of feature extraction and the transmission of image pair characteristics. However, most fusion approaches based on deep learning do not make effective use of the features for image fusion, which results in missing semantic content in the fused image. In this paper, a novel trustworthy image fusion method is proposed to address these issues, which applies convolutional neural networks for feature extraction and blockchain technology to protect sensitive information. The new method can effectively reduce the loss of feature information by making the output of the feature extraction network in each convolutional layer to be fed to the next layer along with the production of the previous layer, and in order to ensure the similarity between the fused image and the original image, the original input image feature map is used as the input of the reconstruction network in the image reconstruction network. Compared to other methods, the experimental results show that our proposed method can achieve better quality and satisfy human perception.
- Open Access
- 26 November 2020
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2020, 1-10
Neural Model Stealing Attack to Smart Mobile Device on Intelligent Medical Platform
To date, the Medical Internet of Things (MIoT) technology has been recognized and widely applied due to its convenience and practicality. The MIoT enables the application of machine learning to predict diseases of various kinds automatically and accurately, assisting and facilitating effective and efficient medical treatment. However, the MIoT are vulnerable to cyberattacks which have been constantly advancing. In this paper, we establish a MIoT platform and demonstrate a scenario where a trained Convolutional Neural Network (CNN) model for predicting lung cancer complicated with pulmonary embolism can be attacked. First, we use CNN to build a model to predict lung cancer complicated with pulmonary embolism and obtain high detection accuracy. Then, we build a copycat model using only a small amount of data labeled by the target network, aiming to steal the established prediction model. Experimental results prove that the stolen model can also achieve a relatively high prediction outcome, revealing that the copycat network could successfully copy the prediction performance from the target network to a large extent. This also shows that such a prediction model deployed on MIoT devices can be stolen by attackers, and effective prevention strategies are open questions for researchers.
- 26 November 2020
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2020, 1-10
Open AccessNeural Model Stealing Attack to Smart Mobile Device on Intelligent Medical Platform
To date, the Medical Internet of Things (MIoT) technology has been recognized and widely applied due to its convenience and practicality. The MIoT enables the application of machine learning to predict diseases of various kinds automatically and accurately, assisting and facilitating effective and efficient medical treatment. However, the MIoT are vulnerable to cyberattacks which have been constantly advancing. In this paper, we establish a MIoT platform and demonstrate a scenario where a trained Convolutional Neural Network (CNN) model for predicting lung cancer complicated with pulmonary embolism can be attacked. First, we use CNN to build a model to predict lung cancer complicated with pulmonary embolism and obtain high detection accuracy. Then, we build a copycat model using only a small amount of data labeled by the target network, aiming to steal the established prediction model. Experimental results prove that the stolen model can also achieve a relatively high prediction outcome, revealing that the copycat network could successfully copy the prediction performance from the target network to a large extent. This also shows that such a prediction model deployed on MIoT devices can be stolen by attackers, and effective prevention strategies are open questions for researchers.