Xiaoyu Cui
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
Xiaoyu Cui has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Bo Zhao
Institute of Medical Intelligence, School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China
1 shared publication- Lei Cui
Guangxi Normal University, Guilin, China and Harbin Institute of Technology, Harbin, China
1 shared publication Wei Cai
Zhongguancun Laboratory, Beijing, China
1 shared publication- Wei Peng
Institute of Information Engineering Chinese Academy of Sciences Beijing China
1 shared publication Wei Wang
Zhongguancun Laboratory, Beijing, China
1 shared publication- Xiaochun Yun
Zhongguancun Laboratory, Beijing, China
1 shared publication
Latest Publications
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 1794-1806
Bottom Aggregating, Top Separating: An Aggregator and Separator Network for Encrypted Traffic Understanding
Encrypted traffic classification refers to the task of identifying the application, service or malware associated with network traffic that is encrypted. Previous methods mainly have two weaknesses. Firstly, from the perspective of word-level (namely, byte-level) semantics, current methods use pre-training language models like BERT, learned general natural language knowledge, to directly process byte-based traffic data. However, understanding traffic data is different from understanding words in natural language, using BERT directly on traffic data could disrupt internal word sense information so as to affect the performance of classification. Secondly, from the perspective of packet-level semantics, current methods mostly implicitly classify traffic using abstractive semantic features learned at the top layer, without further explicitly separating the features into different space of categories, leading to poor feature discriminability. In this paper, we propose a simple but effective Aggregator and Separator Network (ASNet) for encrypted traffic understanding, which consists of two core modules. Specifically, a parameter-free word sense aggregator enables BERT to rapidly adapt to understanding traffic data and keeping the complete word sense without introducing additional model parameters. And a category-constrained semantics separator with task-aware prompts (as the stimulus) is introduced to explicitly conduct feature learning independently in semantic spaces of different categories. Experiments on five datasets across seven tasks demonstrate that our proposed model achieves the current state-of-the-art results without pre-training in both the public benchmark and real-world collected traffic dataset. Statistical analyses and visualization experiments also validate the interpretability of the core modules. Furthermore, what is important is that ASNet does not need pre-training, which dramatically reduces the cost of computing power and time. The model code and dataset will be released in https://github.com/pengwei-iie/ASNET.
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 1794-1806
Bottom Aggregating, Top Separating: An Aggregator and Separator Network for Encrypted Traffic Understanding
Encrypted traffic classification refers to the task of identifying the application, service or malware associated with network traffic that is encrypted. Previous methods mainly have two weaknesses. Firstly, from the perspective of word-level (namely, byte-level) semantics, current methods use pre-training language models like BERT, learned general natural language knowledge, to directly process byte-based traffic data. However, understanding traffic data is different from understanding words in natural language, using BERT directly on traffic data could disrupt internal word sense information so as to affect the performance of classification. Secondly, from the perspective of packet-level semantics, current methods mostly implicitly classify traffic using abstractive semantic features learned at the top layer, without further explicitly separating the features into different space of categories, leading to poor feature discriminability. In this paper, we propose a simple but effective Aggregator and Separator Network (ASNet) for encrypted traffic understanding, which consists of two core modules. Specifically, a parameter-free word sense aggregator enables BERT to rapidly adapt to understanding traffic data and keeping the complete word sense without introducing additional model parameters. And a category-constrained semantics separator with task-aware prompts (as the stimulus) is introduced to explicitly conduct feature learning independently in semantic spaces of different categories. Experiments on five datasets across seven tasks demonstrate that our proposed model achieves the current state-of-the-art results without pre-training in both the public benchmark and real-world collected traffic dataset. Statistical analyses and visualization experiments also validate the interpretability of the core modules. Furthermore, what is important is that ASNet does not need pre-training, which dramatically reduces the cost of computing power and time. The model code and dataset will be released in https://github.com/pengwei-iie/ASNET.
- 16 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (1) , 806-813
Structural Characterization and Optical Properties of Perovskite Crystals Based on Micro-Hyperspectral Imaging Sensor
Micro-hyperspectral imaging (MHSI) is an advanced sensor technology that exploits the distinct spectral signatures of samples for characterization, analysis, and identification. However, applying MHSI to the studies of materials at micro- and nano-scale remains constrained. Perovskite, an innovative material, has attracted widespread attention due to its exceptional optical properties, and the characterizing utilization of MHSI on micro- and nano-scale perovskite crystals represents a novel perspective for further comprehensive analysis of the optical characteristics of perovskite. In this study, we developed a home-built MHSI sensor system through the integration of a hyperspectral imaging sensor and a metallurgical micro-scope, enabling the acquisition of three-dimensional data of the micro-scale perovskite crystals (MAPbBr 3 ) samples, which including the characterization imaging of the morphological structure of the samples and its high-resolution spectral response values for hundreds of spectral bands. Auxiliary verification methodologies, including white light interference, energy dispersive spectroscopy, and COMSOL simulation, were employed for the cross-analysis of complex interrelationships among compositional ratios, thickness, morphology, and optical properties in perovskite crystals (MAPbBr 3 ), and to substantiate the data acquired by MHSI. Specifically, the relationship between thickness and elemental ratios of the crystal has been investigated to explain the optical properties of the ’fishbone’ sample, and morphology features have been studied to verify the optical properties of the ’pyramid’ sample. The strong correlation between the experimental results and auxiliary verification highlights the immense potential of MHSI sensor technology for the characterization and extensive in-depth optical analysis of micro-nano materials.
- 16 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (1) , 806-813
Structural Characterization and Optical Properties of Perovskite Crystals Based on Micro-Hyperspectral Imaging Sensor
Micro-hyperspectral imaging (MHSI) is an advanced sensor technology that exploits the distinct spectral signatures of samples for characterization, analysis, and identification. However, applying MHSI to the studies of materials at micro- and nano-scale remains constrained. Perovskite, an innovative material, has attracted widespread attention due to its exceptional optical properties, and the characterizing utilization of MHSI on micro- and nano-scale perovskite crystals represents a novel perspective for further comprehensive analysis of the optical characteristics of perovskite. In this study, we developed a home-built MHSI sensor system through the integration of a hyperspectral imaging sensor and a metallurgical micro-scope, enabling the acquisition of three-dimensional data of the micro-scale perovskite crystals (MAPbBr 3 ) samples, which including the characterization imaging of the morphological structure of the samples and its high-resolution spectral response values for hundreds of spectral bands. Auxiliary verification methodologies, including white light interference, energy dispersive spectroscopy, and COMSOL simulation, were employed for the cross-analysis of complex interrelationships among compositional ratios, thickness, morphology, and optical properties in perovskite crystals (MAPbBr 3 ), and to substantiate the data acquired by MHSI. Specifically, the relationship between thickness and elemental ratios of the crystal has been investigated to explain the optical properties of the ’fishbone’ sample, and morphology features have been studied to verify the optical properties of the ’pyramid’ sample. The strong correlation between the experimental results and auxiliary verification highlights the immense potential of MHSI sensor technology for the characterization and extensive in-depth optical analysis of micro-nano materials.