Xiaojuan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaojuan Zhang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Baiji Hu
Information and Communication Department, China Electrical Power Research Institute Department, Beijing, China
1 shared publication - Lei Mei
Center for Cyber Security, School of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China
1 shared publication - Mingliang Chen
State Grid JiangXi Electric Power Co., Ltd., China
1 shared publication - Sheng Yuan
University of Electronic Science and Technology of China, China
1 shared publication - Yayun Zhu
China Electric Power Research Institute Co., Ltd., China
1 shared publication
Latest Publications
- Open Access
- 30 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 280-285
The Cryptographic Algorithm Identification: Using Deep Learning to Empower Smart Grids
The smart grid has now been fully implemented with a robust defense system that is built on the primary security principles of “security zoning, network specialization, horizontal isolation, and vertical authentication.” The secure cryptographic module plays a pivotal role as one of the key components in the power system, facilitating horizontal isolation and vertical authentication. Nevertheless, assessing secure cryptographic modules within power systems presents several challenges. These include low recognition efficiency of cryptographic algorithms, the difficulty in identifying the characteristics of encryption algorithm variants, and challenges specific to special business scenarios. To address these issues, this paper introduces an automatic cryptographic algorithm recognition method. Leveraging a deep learning framework in conjunction with modules such as data encryption, data enhancement, feature extraction, model construction, and five-fold cross-validation, this method achieves automated recognition of cryptographic algorithms, enhancing the testing capabilities of secure cryptographic modules. The experiments reveal that cryptographic algorithm detection using deep learning offers significant advantages, including a high recognition success rate, strong adaptability, and a high degree of automation. This method proves beneficial in significantly enhancing the efficiency of security evaluation and modification, effectively detecting the ciphertext features of commercial codes, and providing vital support for the secure operation of the smart grid.
- 30 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 280-285
Open AccessThe Cryptographic Algorithm Identification: Using Deep Learning to Empower Smart Grids
The smart grid has now been fully implemented with a robust defense system that is built on the primary security principles of “security zoning, network specialization, horizontal isolation, and vertical authentication.” The secure cryptographic module plays a pivotal role as one of the key components in the power system, facilitating horizontal isolation and vertical authentication. Nevertheless, assessing secure cryptographic modules within power systems presents several challenges. These include low recognition efficiency of cryptographic algorithms, the difficulty in identifying the characteristics of encryption algorithm variants, and challenges specific to special business scenarios. To address these issues, this paper introduces an automatic cryptographic algorithm recognition method. Leveraging a deep learning framework in conjunction with modules such as data encryption, data enhancement, feature extraction, model construction, and five-fold cross-validation, this method achieves automated recognition of cryptographic algorithms, enhancing the testing capabilities of secure cryptographic modules. The experiments reveal that cryptographic algorithm detection using deep learning offers significant advantages, including a high recognition success rate, strong adaptability, and a high degree of automation. This method proves beneficial in significantly enhancing the efficiency of security evaluation and modification, effectively detecting the ciphertext features of commercial codes, and providing vital support for the secure operation of the smart grid.