Cheng Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Cheng Zhu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Guang Cheng
School of Cyber Science and Engineering, Southeast University, Nanjing 211189, China
2 shared publications - Jian Gong
School of Cyber Science and Engineering, Southeast University, Nanjing, China
2 shared publications - Ruidong Li
Institute of Science and Engineering, Kanazawa University, Kakuma, Kanazawa, Japan
2 shared publications - Xiaoyan Hu
School of Cyber Science and Engineering, Southeast University, Nanjing, China
2 shared publications Hua Wu
School of Cyber Science and Engineering, Southeast University, Nanjing, China
1 shared publication- Hua Wu
School of Cyber Science and Engineering, Southeast University, Nanjing, China
1 shared publication
Latest Publications
- 21 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (5) , 3814-3826
A Deep Subdomain Adaptation Network With Attention Mechanism for Malware Variant Traffic Identification at an IoT Edge Gateway
The prevailing of malware variants in ubiquitous Internet of Things (IoT) devices causes enormous losses. Accurate and timely identification of malware variant traffic at an IoT edge gateway can effectively reduce the loss. TransNet, the state-of-the-art technology for malware variant traffic detection, considers only global domain adaptation and ignores the alignment of distributions between different subdomains, which fails to capture the fine-grained information of classification targets. Besides, TransNet converges very slowly, which may use up precious resources in IoT devices. This article proposes a deep subdomain adaptation network with attention mechanism (DSAN-AT) to accurately and efficiently identify malware variant traffic at an IoT edge gateway. DSAN-AT utilizes local maximum mean discrepancy (LMMD) to align the traffic feature distributions of subdomains in the source and target domains. It also exploits channel and spatial attention mechanisms to accelerate learning traffic features between different subdomains to save precious computing resources at the IoT edge gateway. Our experimental study demonstrates that DSAN-AT achieves an average accuracy of 97.15% (96.37% for TransNet) and converges fast without using a large target domain training data set. DSAN-AT has strong practicality for identifying malware variant traffic at an edge IoT gateway.
- 21 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (5) , 3814-3826
A Deep Subdomain Adaptation Network With Attention Mechanism for Malware Variant Traffic Identification at an IoT Edge Gateway
The prevailing of malware variants in ubiquitous Internet of Things (IoT) devices causes enormous losses. Accurate and timely identification of malware variant traffic at an IoT edge gateway can effectively reduce the loss. TransNet, the state-of-the-art technology for malware variant traffic detection, considers only global domain adaptation and ignores the alignment of distributions between different subdomains, which fails to capture the fine-grained information of classification targets. Besides, TransNet converges very slowly, which may use up precious resources in IoT devices. This article proposes a deep subdomain adaptation network with attention mechanism (DSAN-AT) to accurately and efficiently identify malware variant traffic at an IoT edge gateway. DSAN-AT utilizes local maximum mean discrepancy (LMMD) to align the traffic feature distributions of subdomains in the source and target domains. It also exploits channel and spatial attention mechanisms to accelerate learning traffic features between different subdomains to save precious computing resources at the IoT edge gateway. Our experimental study demonstrates that DSAN-AT achieves an average accuracy of 97.15% (96.37% for TransNet) and converges fast without using a large target domain training data set. DSAN-AT has strong practicality for identifying malware variant traffic at an edge IoT gateway.
- 24 February 2022
- Published by Elsevier in Future Generation Computer Systems
- Vol. 132, 162-177
Identifying Ethereum traffic based on an active node library and DEVp2p features
- 24 February 2022
- Published by Elsevier in Future Generation Computer Systems
- Vol. 132, 162-177
Identifying Ethereum traffic based on an active node library and DEVp2p features
- Open Access
- 7 April 2020
- Published by Oxford University Press (OUP) in International Journal of Low-Carbon Technologies
- Vol. 15 (3) , 409-413
The influence of cement-based composite materials on the performance of bridges: modification and optimization by nano-SiO2 material
Cement-based materials have been widely used in bridge construction. In order to further improve their performance, this study analyzed the modification and optimization functions of nano-SiO2 materials, designed test specimens with different content of nano-SiO2 and conducted experiments on their flow performance, compression resistance, bending resistance and impermeability. The results showed that the flow performance of the materials decreased and the impermeability decreased with the increase of nano-SiO2 content. The compressive strength and flexural strength are the best when the content of nano-SiO2 is 1%. On the whole, the best content of nano-SiO2 is 1%; when the content of nano-SiO2 is 1%, all the properties of the specimens are good, which is more conducive to the construction of bridges in various complex environments. The research in this paper has made some contributions to the further application of nano-SiO2 in the optimization of building materials, which is conducive to the better development of building materials.
- 7 April 2020
- Published by Oxford University Press (OUP) in International Journal of Low-Carbon Technologies
- Vol. 15 (3) , 409-413
Open AccessThe influence of cement-based composite materials on the performance of bridges: modification and optimization by nano-SiO2 material
Cement-based materials have been widely used in bridge construction. In order to further improve their performance, this study analyzed the modification and optimization functions of nano-SiO2 materials, designed test specimens with different content of nano-SiO2 and conducted experiments on their flow performance, compression resistance, bending resistance and impermeability. The results showed that the flow performance of the materials decreased and the impermeability decreased with the increase of nano-SiO2 content. The compressive strength and flexural strength are the best when the content of nano-SiO2 is 1%. On the whole, the best content of nano-SiO2 is 1%; when the content of nano-SiO2 is 1%, all the properties of the specimens are good, which is more conducive to the construction of bridges in various complex environments. The research in this paper has made some contributions to the further application of nano-SiO2 in the optimization of building materials, which is conducive to the better development of building materials.