Yong Li
Research Subjects
Yong Li has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Bo Zhang
China Electric Power Research Institute, Beijing, China
1 shared publication - Cen Chen
State Grid Henan Electric Power Research Institute, China
1 shared publication - Chen Wang
State Grid Smart Grid Research Institute Co., Ltd, China
1 shared publication - Chen Wang
State Grid Smart Grid Research Institute Co., Ltd., China
1 shared publication - ChengFei Yu
State Grid JiangXi Electric Power Co., Ltd., China
1 shared publication - Chuan He
School of Cyber Science and Engineering, Southeast University, Sipailou 2, Nanjing, 210096, China; China Electric Power Research Institute, Nanrui Road 8, Nanjing, 210003, China
1 shared publication
Latest Publications
- Open Access
- 7 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 39-43
Power terminal anomaly monitoring technology based on autoencoder and multi-layer perceptron
A terminal anomaly monitoring method based on an improved autoencoder and multi-layer perceptron (MLP) is proposed to address the complex problem of determining user side business ownership in a new power system. This method uses Minimum Gating Unit (MGU) to replace ordinary neural networks in traditional autoencoders for data feature extraction, improving the model's temporal modeling ability. Then, multi-layer perceptrons are used to complete terminal traffic analysis tasks and achieve terminal abnormal behavior detection. The experimental results show that this method is significantly superior to traditional classification methods in performance indicators such as accuracy, recall, precision, and F1 score.t.
- 7 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 39-43
Open AccessPower terminal anomaly monitoring technology based on autoencoder and multi-layer perceptron
A terminal anomaly monitoring method based on an improved autoencoder and multi-layer perceptron (MLP) is proposed to address the complex problem of determining user side business ownership in a new power system. This method uses Minimum Gating Unit (MGU) to replace ordinary neural networks in traditional autoencoders for data feature extraction, improving the model's temporal modeling ability. Then, multi-layer perceptrons are used to complete terminal traffic analysis tasks and achieve terminal abnormal behavior detection. The experimental results show that this method is significantly superior to traditional classification methods in performance indicators such as accuracy, recall, precision, and F1 score.t.
- Open Access
- 19 January 2024
- Published by Association for Computing Machinery (ACM)
- p. 75-80
Research on Flexible Secure Access and Unknown Attack Awareness Technology for New-type Business Terminals
The characteristics of the new-type business terminals, such as the integration of various applications, complex external interactions and enhanced edge intelligence, pose three major challenges to the security protection of the company. These challenges encompass creating significant difficulties for security protection systems based on boundary isolation, existing authentication methods facing challenges in maintaining a balance between security and flexibility, and the incapacity to identify unknown attacks. To address the security issues arising from the widespread integration of new-type business terminals, the increasingly blurred network boundaries, and the significantly enlarged system exposure surface, this article develops a terminal-side prototype with flexible secure access and unknown attack awareness and defense. This paper also creates a secure access gateway with the capability to perceive and defend against unknown attacks. In addition, pilot verifications are conducted in typical scenarios of new-type business terminals, offering efficient and flexible secure access, cloud-edge collaborative defense against unknown attacks, and other technological support. Therefore, we are able to provide precise and adequate defense capabilities to ensure the efficient development of new-type power system business.
- 19 January 2024
- Published by Association for Computing Machinery (ACM)
- p. 75-80
Open AccessResearch on Flexible Secure Access and Unknown Attack Awareness Technology for New-type Business Terminals
The characteristics of the new-type business terminals, such as the integration of various applications, complex external interactions and enhanced edge intelligence, pose three major challenges to the security protection of the company. These challenges encompass creating significant difficulties for security protection systems based on boundary isolation, existing authentication methods facing challenges in maintaining a balance between security and flexibility, and the incapacity to identify unknown attacks. To address the security issues arising from the widespread integration of new-type business terminals, the increasingly blurred network boundaries, and the significantly enlarged system exposure surface, this article develops a terminal-side prototype with flexible secure access and unknown attack awareness and defense. This paper also creates a secure access gateway with the capability to perceive and defend against unknown attacks. In addition, pilot verifications are conducted in typical scenarios of new-type business terminals, offering efficient and flexible secure access, cloud-edge collaborative defense against unknown attacks, and other technological support. Therefore, we are able to provide precise and adequate defense capabilities to ensure the efficient development of new-type power system business.
- Open Access
- 19 January 2024
- Published by Association for Computing Machinery (ACM)
- p. 11-16
Software-define cloud-edge collaborative defense architecture against unknown attacks
In the scenario of new service terminal access, the targets of unknown attacks are random and diverse, the attack paths are dynamically variable, and the attack means are heterogeneous and diverse, showing the characteristics of random and decentralized. At the same time, the existing static network defense framework has the problems of insufficient flexibility and inability to adjust the defense strategy in time and effectively, which makes it difficult to intercept and deal with the above unknown attacks. Aiming at these problems, this paper proposes a software-defined cloud-edge collaborative defense architecture for unknown attacks. Through the flexibility and programmability of software-defined network technology, the architecture realizes efficient cooperation between the cloud (master station) and the edge station. This paper systematically introduces how to integrate the network resources of cloud and edge by constructing software-defined security platform technology on the master side, so as to realize the full-link unknown attack detection and collaborative defense mechanism.
- 19 January 2024
- Published by Association for Computing Machinery (ACM)
- p. 11-16
Open AccessSoftware-define cloud-edge collaborative defense architecture against unknown attacks
In the scenario of new service terminal access, the targets of unknown attacks are random and diverse, the attack paths are dynamically variable, and the attack means are heterogeneous and diverse, showing the characteristics of random and decentralized. At the same time, the existing static network defense framework has the problems of insufficient flexibility and inability to adjust the defense strategy in time and effectively, which makes it difficult to intercept and deal with the above unknown attacks. Aiming at these problems, this paper proposes a software-defined cloud-edge collaborative defense architecture for unknown attacks. Through the flexibility and programmability of software-defined network technology, the architecture realizes efficient cooperation between the cloud (master station) and the edge station. This paper systematically introduces how to integrate the network resources of cloud and edge by constructing software-defined security platform technology on the master side, so as to realize the full-link unknown attack detection and collaborative defense mechanism.