A5100544650- Advanced Malware Detection Techniques
- Network Security and Intrusion Detection
- Software Testing and Debugging Techniques
- Digital and Cyber Forensics
- Spam and Phishing Detection
- Water Quality Monitoring and Analysis
- Information and Cyber Security
- Telecommunications and Broadcasting Technologies
- User Authentication and Security Systems
- Natural Language Processing Techniques
- Topic Modeling
- Adsorption and biosorption for pollutant removal
- Geochemistry and Elemental Analysis
- Software Reliability and Analysis Research
- Image and Video Quality Assessment
- Heavy metals in environment
- Advanced Data Compression Techniques
Shanghai Institute of Optics and Fine Mechanics
2025
University of Chinese Academy of Sciences
2025
Tianjin University
2024
Beijing University of Posts and Telecommunications
2017-2020
China Information Technology Security Evaluation Center
2019-2020
In recent years, cyber criminals have successfully invaded many important information systems by using phishing mail, causing huge losses. The detection of mail from big email data has been paid public attention. However, the camouflage technology is becoming more and complex, existing methods are unable to confront with increasingly complex deception growing number emails. this article, we proposed an LSTM based method for data. new includes two stages, sample expansion stage testing under...
Heavy metals in liquid seriously harm the environment and threaten human health. The fluorescence detection system based on probe method has advantages of small size fast speed, which is helpful to understand pollution status environmental risk groundwater provide scientific basis for treatment. However, long time laser irradiation fluorescent produces photobleaching phenomenon, weakens signal intensity. excitation noise confocal optical path high, resulting low signal-to-noise ratio, cannot...
With the development of malicious code engineering, new malware samples carry variability and polymorphism, which makes variants show an increasingly growing trend. Traditional signature-based detection methods can hardly detect such so that it is significant for cyber security field to analyze large-scale by means machine learning. Based on 65,536 samples, this paper proposed a classification method family basis static feature extraction using features from three aspects including bytecode...
Android app clone detection has been extensively studied in our community, and a number of effective approaches frameworks were proposed released.However, there still remains one open challenge that not well addressed previous work, i.e., the authorship attribution for detected clones.Although state-of-the-art could accurately identify repackaged apps way or another, no convincing method to original authentic author from pairs, which greatly limits usage scenario techniques.For example,...
In recent years, the threat of malware in Internet is extremely serious, detection becomes one most challenging task cyberspace. this paper, we propose a novel method using code image and nerual network. We enhanced traditional gray with visible string PE file structure to RGB image, then put into top 13 layer VGG16, finally use Spp-Net adapt feature size. order make label reliable, various Virustotal result get voting result, algorithm train predict malware. test proposed real datasets,...
At present, fuzzy test is one of the most common ways software vulnerability mining. However, pertinence traditional not strong enough, coverage too low. The can't meet demand safety requirements industrial control systems. This paper aimed at characteristics terminal equipment. We use genetic algorithm to design variation function and improve memory detect vulnerabilities. Based on this paper, we can effectively implement new mining system for terminal, greatly shorten excavation time.