A5022700172- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Artificial Immune Systems Applications
- Software Testing and Debugging Techniques
- Anomaly Detection Techniques and Applications
- Security and Verification in Computing
- Face and Expression Recognition
- Educational Technology and Assessment
- Imbalanced Data Classification Techniques
- Internet Traffic Analysis and Secure E-voting
- vaccines and immunoinformatics approaches
- Influenza Virus Research Studies
- Digital and Cyber Forensics
- Higher Education and Teaching Methods
- Evolutionary Algorithms and Applications
- Neural Networks and Applications
- Information and Cyber Security
Sichuan University
2023-2025
Xinjiang University
2020
Wuhan Textile University
2013
Android malware and its variants are a major challenge for mobile platforms. However, there two main problems in the existing detection methods: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a</i> ) The method lacks evolution ability malware, which leads to low rate of model variants. xmlns:xlink="http://www.w3.org/1999/xlink">b</i> Traditional methods require centralized data training, however, aggregation training samples is limited due...
Unmanned aerial vehicles (UAVs) have experienced rapid development, permeating diverse domains. However, addressing security challenges in UAV networks remains daunting due to resource limitations and the high autonomy of terminals. The current research on network intrusion detection lacks an efficient process covering each terminal a lightweight collaborative response mechanism between UAVs ground stations, which affects performance detection. In this article, inspired by vaccine...
Application‐layer distributed denial of service (DDoS) attacks have become the main threat to Web server security. Because application‐layer DDoS strong concealability and high authenticity, intrusion detection technologies that rely solely on judging client authenticity cannot accurately detect such attacks. In addition, are periodic repetitive, attack targets suddenly in a short period. this study, we propose an efficient system based improved random forest. Firstly, logs preprocessed...
Given the continual evolution of new network attack methodologies, defenders face imperative constantly upgrading security defenses. Current technologies, albeit effective against known threats, often fall short in handling intricacies diverse and novel attacks. Artificial immunity-based anomaly detection offers a promising avenue by dynamically adapting to evolving threats. However, prevailing algorithms this domain suffer from low rates, limited adaptability, extended detector generation...
With the continuous expansion of Android operating system and market for mobile apps continues to expand, number malwares designed is also exploding. Therefore, identifying detecting malware becomes a challenging task in security. Because low detection efficiency by using traditional machine learning methods, we propose novel method based on multi-model deep learning. Specifically, select four features permissions, API, Intent, hardware components build feature vector each app. In our study,...
Abstract The problem of data imbalance is common in reality, which greatly affects the performance classifiers. Most solutions are to balance set by generating new minority class samples, faced with problems selecting appropriate area for fuzzy classification boundary and uneven distribution samples. To solve these problems, we propose a novel oversampling algorithm named space partitioning adaptive weighted synthetic technique (SPAW-SMOTE). We first divide into non-boundary based on spatial...