A5051542048- Network Security and Intrusion Detection
- Internet Traffic Analysis and Secure E-voting
- Privacy-Preserving Technologies in Data
- Vehicular Ad Hoc Networks (VANETs)
- Cryptography and Data Security
- Mobile Crowdsensing and Crowdsourcing
- Anomaly Detection Techniques and Applications
- Advanced Malware Detection Techniques
- Advanced Steganography and Watermarking Techniques
- Topic Modeling
- Cloud Computing and Resource Management
- Domain Adaptation and Few-Shot Learning
- Video Surveillance and Tracking Methods
- Text and Document Classification Technologies
- Cognitive Functions and Memory
- Digital and Cyber Forensics
- Advanced Database Systems and Queries
- Access Control and Trust
- Service-Oriented Architecture and Web Services
- Digital Media Forensic Detection
- Data-Driven Disease Surveillance
Shanghai Electric (China)
2022-2025
ABSTRACT With the rise of social media and spread a large number pictures on Internet, protecting data privacy verifying copyright has become hot research. A common method is to use digital watermarking. However, existing blind watermarking methods only consider embedding watermark in image itself ignore fact that attacker can remove through other shooting devices. Therefore, solve this problem, we propose an based few‐shot learning. We autoencoder learn extraction watermarks. Then,...
Network traffic classification has become an important part of network management, which is conducive to realizing intelligent operation and maintenance, improving quality service (QoS), ensuring security. With the rapid development various applications protocols, more encrypted appears in network. Due loss semantic information after encryption, poor content intelligibility, difficulty feature extraction, traditional detection methods are no longer applicable. Existing solutions mainly rely...
This paper presents a feature fusion and sparse transformer-based anomalous traffic detection system (FSTDS). FSTDS utilizes network to encode the data sequences extracting features, fusing them into coding vectors through shallow deep convolutional networks, followed by using transformer capture complex relationships between flows; finally, multilayer perceptron is used classify achieve anomaly detection. The of improves extraction from small sample data, encoder enhances understanding...
Traditional machine learning-based entity extraction methods rely heavily on feature engineering by experts, and the generalization ability of model is poor. Prototype networks, other hand, can effectively use a small amount labeled data to train models while using category prototypes enhance models. Therefore, this paper proposes prototype network-based named recognition (NER) method, namely FSPN-NER model, solve problem difficult sensitive in data-sparse text. The utilizes positional...
The goal of privacy-preserving social graph publishing is to protect individual privacy while preserving utility. Node nearest neighbor structure a crucial utility as it the basis for many analysis tasks. Most existing methods with differential focus on degree distribution yet neglect maintenance connections between nodes' neighbors. Moreover, they require massive noise added mask change single edge, thereby rendering poor structure. As result, tough preserve high under privacy. To tackle...
This paper first introduces the performance dilemma faced by OLAP database, and then combines operational characteristics of OLTP innovatively adopts loosely coupled distributed architecture, designs a high-performance database integrating transaction analysis (DITAA), analyzes its structure data, queries number scan lines experiment to verify improvement analysis.
Network intrusion detection (NID) has attracted much attention as it is essential in preventing security threats and protecting networks from attacks. However, existing methods face the following challenges: (1) poor feature extraction capability; (2) not well-designed to address class imbalance problem; (3) failure take full use of label information learn classification-oriented features, degrading NID performance. To this end, we proposed SC-Net, a two-stage training model with deep...
The group relationship (Community Relation) contained in the trajectory data can be used for hot spot exploration, community governance, and traffic diversion, which has broad application prospects. Trajectory association privacy refers to user with a similar movement mode data. Publishing analysts without protection will cause leakage of such privacy. Recently, correlation attracted attention researchers, proposing solutions based on differential Still, existing methods are limited...