A5068116051- Internet Traffic Analysis and Secure E-voting
- Network Security and Intrusion Detection
- Spam and Phishing Detection
- Advanced Malware Detection Techniques
- Speech Recognition and Synthesis
- 3D Shape Modeling and Analysis
- Music and Audio Processing
- Voice and Speech Disorders
- Human Motion and Animation
- Natural Language Processing Techniques
- Sentiment Analysis and Opinion Mining
- Security in Wireless Sensor Networks
- Textile materials and evaluations
- Network Packet Processing and Optimization
- Advanced Vision and Imaging
- Caching and Content Delivery
- Advanced Text Analysis Techniques
- Pituitary Gland Disorders and Treatments
- Growth Hormone and Insulin-like Growth Factors
- Biomedical Ethics and Regulation
- Wireless Communication Security Techniques
- Computer Graphics and Visualization Techniques
- Software Testing and Debugging Techniques
- Text and Document Classification Technologies
- Indoor and Outdoor Localization Technologies
Sichuan Mianyang 404 Hospital
2025
Orthopaedic Hospital
2025
Zhejiang University of Finance and Economics
2023
National University of Singapore
2023
Institute of Information Engineering
2019-2022
Chinese Academy of Sciences
2019-2022
University of Chinese Academy of Sciences
2017-2022
Chongqing University
2021
Malware remains the most significant security threat to smartphones in spite of constantly upgrading system. In this paper, we introduce an Android malware detection method based on XGBoost model. We subsequently discuss effect feature selection classification. end, verify high efficacy and good accuracy model through experiment, which achieves similar results SVM while spending less time.
Domain-squatting abuse refers to the premeditated attempt by an attacker register perceptively confusing domain names thereby tricking visitors into querying them. There are totally five squatting types have been investigated so far, namely typo-squatting, bit-squatting, homograph-squatting, sound-squatting, and combo-squatting. Existing researches only focus on one specific type never explore relationship among In this paper, we perform first comprehensive measurement study of...
We present ClothesNet: a large-scale dataset of 3D clothes objects with information-rich annotations. Our consists around 4400 models covering 11 categories annotated features, boundary lines, and keypoints. ClothesNet can be used to facilitate variety computer vision robot interaction tasks. Using our dataset, we establish benchmark tasks for perception, including classification, line segmentation, keypoint detection, develop simulated environments robotic tasks, rearranging, folding,...
Malicious domain detection is of great significance for cybersecurity. Most prior works detect malicious domains based on individual features, which are only related to the attributes themselves and can be easily changed avoid detection. To solve problem, we propose a novel system called MalPortrait, combines features association information domains. In show among by graph where vertices represent edges connect resolved same IP. Based graph, combine (e.g., string-based, network-based) each...
URL redirection has become an important tool for adversaries to cover up their malicious campaigns. In this paper, we conduct the first large-scale measurement study on how leverage circumvent security checks and distribute content in practice. To end, design iteratively running framework mine domains used redirections constantly. First, use a bipartite graph-based method dig out potentially involved from real-world DNS traffic. Then, dynamically crawl these suspicious recover corresponding...
Many botmasters use domain generation algorithms (DGA) to generate a host of malicious algorithmically- generated domains (mAGDs) and then choose several mAGDs for actual command control (C2) communication. The different seeds (e.g., timestamp) mAGDs, which makes the communication mechanism resilient blacklisting. Thus can hide C2 channels very well. If we quickly detect these from DNS traffic, will effectively block In this paper, propose novel system, called Pontus, traffic. Pontus extract...
More Internet services tend to collect the one-time information from clients via DNS queries. Notably, uncertainty of such transient makes these domain names be queried only once in their lifetime. This type is called disposable domain. Although they are not malicious, efficiency infrastructures will still affected by ever-increasing number. In this paper, we propose Vogers, a linguistics-based stacking model, detect domains. Our evaluation demonstrates that Vogers decreases false positive...
Diagnosis and therapeutic effect assessment of Parkinson disease based on voice data are very important,but its few-shot learning problem is challenging.Although deep good at automatic feature extraction, it suffers from problem. Therefore, the general effective method first conduct extraction prior knowledge, then carry out reduction for subsequent classification. However, there two major problems: 1) Structural information among speech features has not been mined new higher quality have...
We present ClothesNet: a large-scale dataset of 3D clothes objects with information-rich annotations. Our consists around 4400 models covering 11 categories annotated features, boundary lines, and keypoints. ClothesNet can be used to facilitate variety computer vision robot interaction tasks. Using our dataset, we establish benchmark tasks for perception, including classification, line segmentation, keypoint detection, develop simulated environments robotic tasks, rearranging, folding,...
When applying the popular deep learning based NL2SQL models directly in a specific scenario, problems arise due to characteristics rooted background knowledge. In our case, terminologies and abbreviations high value payment system database are main obstacles. this paper, framework that is compatible with BERT-CN RAT-SQL proposed for data inquiry tasks within system, which both BERT state of art achieved great performance many tasks. Besides that, NER preprocessing toolkits introduced align...