A5062395976- Advanced Image Fusion Techniques
- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Infrared Target Detection Methodologies
- Remote-Sensing Image Classification
- Photoacoustic and Ultrasonic Imaging
- Internet Traffic Analysis and Secure E-voting
- Anomaly Detection Techniques and Applications
Chinese Academy of Sciences
2018-2025
Changchun Institute of Optics, Fine Mechanics and Physics
2025
Institute of Information Engineering
2016-2018
The principle of the image fusion is to integrate complementary information heterogeneous images obtain a fused that more in line with visual effect human eyes. However, most decomposition methods cannot distinguish textures and edges an image, which easy produce halo artifacts around edges. In this paper, we proposed novel strategy (co-occurrence analysis shearlet transform, CAST) preprocess input depending on co-occurrence statistic generate base layer detail components. order improve...
Because of the rapid increasing malware, one main challenges in malware detection is how to do classification automatically. Although there are many automatic methods recently, their results still get high false positive rate. Since base number samples huge, a very small can cause big alarms. Essentially, rate usually caused by adoption obfuscation and evasion technology malware. As result, or more features would be disguised. In this paper, we propose method using multi-features mitigate...
Nowadays, most botnets utilize domain generation algorithms (DGAs) to build resilient and agile command control (C&C) channels. Specifically, botmasters employ DGAs dynamically produce a large number of random domains only register small subset for their actual C&C servers with the purpose defend them from takeovers blacklisting attempts. While many approaches models have been developed detect DGA-based botnets, they suffer several limitations, such as difficulties DNS traffic collection,...