A5022520936- Internet Traffic Analysis and Secure E-voting
- Advanced Graph Neural Networks
- Peer-to-Peer Network Technologies
- Network Security and Intrusion Detection
- Caching and Content Delivery
- Distributed and Parallel Computing Systems
- Network Traffic and Congestion Control
- Digital Media Forensic Detection
- Advanced Steganography and Watermarking Techniques
Harbin Engineering University
2023-2024
Institute for Infocomm Research
2004-2006
Agency for Science, Technology and Research
2004-2006
Anchor link prediction enhances the effectiveness of digital forensics through identification multiple social network users. The current methods based on deep learning are characterized by both exaggerated similarity between adjacent nodes in same latent space and variation feature spaces caused semantics. A novel approach is developed to fuse semantic features different networks this paper. proposed method divided into two stages. Firstly, representation pays more attention influence...
Anchor link prediction exacerbates the risk of privacy leakage via de-anonymization in edge computing. The predictive effect traditional unsupervised learning methods is too dependent on user attributes and supervised are sensitive to network structure noise. based graph embedding restricted by sparsity observable anchor links which can be used for training. To facilitate effectiveness robustness prediction, we have proposed a novel method reduces restrictions consists two phases. First,...