A5071095256- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Information and Cyber Security
- Digital Media Forensic Detection
- Face recognition and analysis
- Face and Expression Recognition
- Semantic Web and Ontologies
- Domain Adaptation and Few-Shot Learning
- Video Surveillance and Tracking Methods
- Anomaly Detection Techniques and Applications
- Web Data Mining and Analysis
- Music Technology and Sound Studies
- Music and Audio Processing
- Machine Learning and ELM
- Biometric Identification and Security
- Video Analysis and Summarization
- Digital and Cyber Forensics
- Machine Learning and Algorithms
- Data Quality and Management
- Technology and Security Systems
- Machine Learning and Data Classification
- Advanced Graph Neural Networks
- Human Pose and Action Recognition
- Cognitive Computing and Networks
- Generative Adversarial Networks and Image Synthesis
Guangzhou University
2021-2024
Peng Cheng Laboratory
2023-2024
Guangdong Polytechnic Normal University
2020
Deep convolutional neural networks have been successfully applied to face detection recently. Despite making remarkable progress, most of the existing methods only localize each using a bounding box, which cannot segment from background image simultaneously. To overcome this drawback, we present and segmentation method based on improved Mask R-CNN, named G-Mask, incorporates into one framework aiming obtain more fine-grained information face. Specifically, in proposed method, ResNet-101 is...
Intelligent Connected Vehicles (ICVs) are increasingly prevalent, with various applications and systems operating in complex network environments. Consequently, detecting preventing intrusion is important. The Controller Area Network (CAN) presently the predominant vehicles, capturing communication among Electronic Control Units. Such data can facilitate analysis of system anomalies enhance security measures. In response, a novel detection framework proposed, leveraging additive fusion...
The Internet now plays a pivotal role in the social and economic landspace, providing individuals businesses with access to essential daily services tasks. However, it has also become breeding ground for conflicts. Advanced Persistent Threats (APTs) pose formidable chanllenge when directed at organizations governments, exposing entire network substantial security risks. Employing fornesics attributing cyber-attacks acquiring timely, credible forensic results is fundamental challenge...
The widespread dissemination of Deepfake in social networks has posed serious security risks, thus necessitating the development an effective detection technique. Currently, video-based detectors have not been explored as extensively image-based detectors. Most existing methods only consider temporal features without combining spatial features, and do mine deeper-level subtle forgeries, resulting limited performance. In this paper, a novel spatiotemporal trident network (STN) is proposed to...
In recent years, extensive research has been conducted in Advanced Persistent Threat (APT) attack defence. However, most existing defence solutions can only identify and temporarily disrupt cyber attacks, seeking to deny the threat from intranet, it's difficult against APT attacks. Attributing organization is an excellent complement solutions, which not expose attacker's true identity, but also provide evidence bring attacker justice. on attributing Organization still few, poses complex...
The abuse of DeepFakes poses a potential threat to individuals and society. In order eliminate the negative effects techniques, researchers have conducted in-depth research on detection DeepFakes. Despite remarkable progress, there is still lack systematic summarization generation techniques due different focus researchers. this paper, development technology reviewed, existing approaches datasets are systematically summarized scientifically classified. doing so, we hope provide reference for...
With the development of cyberspace and applications, Internet big data has become ubiquitous, which contains important information knowledge. Correspondingly, demand for intelligent search also arisen. IISI, an system, can automatically collect use analysis, natural language processing artificial intelligence technologies to intelligently analyze process data, obtain valuable knowledge contained within construct graphs. By accurately understanding user's intention, system offers data. This...
The corpora in cybersecurity knowledge base is characterized by multi-entity and weak relation. In order to solve the problem that entity extraction, links disambiguation can lead wrong knowledge, a graph construction method for security proposed. At conceptual level, ontology model ontology-instance are constructed based on five-tuple structure, classified associated from horizontal vertical perspectives. data layer, features combined with named recognition model. While recognizing...