Yong Fang

Yong Fang

Auto-generated profile, based on publicly available information

Yong Fang

School of Cyber Science and Engineering, Sichuan University, Chengdu, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 January 2020 in IEEE Access
Verified
Journal Article
Open access
YFYong Fang
Yong Fang
YGYangchen Gao
Yangchen Gao
FJFan Jing
Fan Jing
LZLei Zhang
Lei Zhang
The rapid proliferation of Android malware is challenging the classification of the Android malware family. The traditional static method for classification is easily affected by the confusion and reinforcement, while the dynamic method is expensive in computation. To solve these problems, this paper proposes an Android malware familial classification method based on Dalvik Executable (DEX) file section features. First, the DEX file is converted into RGB (Red/Green/Blue) image and plain text respectively, and then, the color and texture of image and text are extracted as features. Finally, a feature fusion algorithm based on multiple kernel learning is used for classification. In this experiment, the Android Malware Dataset (AMD) was selected as the sample set. Two different comparative experiments were set up, and the method in this paper was compared with the common visualization method and feature fusion method. The results show that our method has a better classification effect with precision, recall and F1 score reaching 0.96. Besides, the time of feature extraction in this paper is reduced by 2.999 seconds compared with the method of frequent subsequence. In conclusion, the method proposed in this paper is efficient and precise in the classification of the Android malware family.

5 October 2018 in IEEE Access
Verified
Journal Article
Open access
YFYong Fang
Yong Fang
CHCheng Huang
Cheng Huang
LLLiang Liu
Liang Liu
MXMin Xue
Min Xue
The attacker injects malicious JavaScript into web pages to achieve the purpose of implanting Trojan horses, spreading viruses, phishing, and obtaining secret information. By analyzing the existing researches on malicious JavaScript detection, a malicious JavaScript detection model based on LSTM (Long Short-Term Memory) is proposed. Features are extracted from the semantic level of bytecode, and the method of word vector is optimized. It can distinguish malicious JavaScript code and combat obfuscated code effectively. Experiments showed that the accuracy of detection model based on LSTM is 99.51%, and the F1-score is 98.37%, which is better than the existing model based on Random Forest and SVM algorithm.

11 April 2019 in IEEE Access
Verified
Journal Article
Open access
YFYong Fang
Yong Fang
YGYusong Guo
Yusong Guo
CHCheng Huang
Cheng Huang
LLLiang Liu
Liang Liu
Recently, underground forums play a crucial role in trading and exchanging leaked personal information. Meanwhile, the forums have been gradually used as data breaches’ information sources. Therefore, it shows an upward trend in announcing the results of data theft by posting in the forums. Identifying these threads can make the compromised third-party respond quickly to the data breach incident. For this purpose, we presented a system to identify the threads which are related to data breaches automatically. The system can monitor and discover data breaches in underground forums in real-time. In addition, the study further revealed the wording characteristics of the threads by applying the feature extraction method based on LDA topic model. In this paper, the data set was collected from the surface web and the dark web. Besides, to improve the performance of the system, we compared various supervised classification algorithms in this application scenario and selected the best method for the classifier. Through the system, we identified more than 92% of data breach threads on the experimental data set.

25 December 2019 in IEEE Access
Verified
Journal Article
Open access
YFYong Fang
Yong Fang
WZWenjie Zhang
Wenjie Zhang
Beibei LiBeibei Li
Beibei Li
FJFan Jing
Fan Jing
LZLei Zhang
Lei Zhang
With the rapid advances of anti-virus and anti-tracking technologies, three aspects in malware clustering need to be improved for effective clustering, i.e., the robustness of features, the accuracy of similarity measurements, and the effectiveness of clustering algorithms. In this paper, we propose a novel malware family clustering approach based on dynamic and static features with their weights. In this approach, we employ a new similarity measurement method based on EMD to improve the accuracy of feature similarities. In addition, to reduce convergence time and improve clustering purity, we design a novel semi-supervised clustering algorithm, termed as S-DBSCAN by involving supervision information into the original algorithm known as Density-Based Spatial Clustering of Applications with Noise (DBSCAN). The experimental results demonstrate that the proposed approach can correctly and accurately distinguish the samples among various families and achieve outperformed purity with 98.7%.

16 April 2020 in International Journal of Distributed Sensor Networks
Verified
Journal Article
Open access
PDF file
FSFan Shi
Fan Shi
PZPengcheng Zhu
Pengcheng Zhu
XZXiangyu Zhou
Xiangyu Zhou
BYBintao Yuan
Bintao Yuan
YFYong Fang
Yong Fang
In recent years, Internet of things (IoT) devices are playing an important role in business, education, medical as well as in other fields. Devices connected to the Internet is much more than the number of world population. However, it may face all kinds of attacks from the Internet easily for its accessibility. As we all know, most attacks against IoT devices are based on Web applications. So protecting the security of Web services can effectively improve the situation of IoT ecosystem. Conventional Web attack detection methods highly rely on samples, and artificial intelligence detection results are uninterpretable. Hence, this article introduced a supervised detection algorithm based on benign samples. Seq2Seq algorithm is been chosen and applied to detect malicious web requests. Meanwhile, the attention mechanism is introduced to label the attack payload and highlight labeling abnormal characters. The results of experiments show that on the premise of training a benign sample, the precision of proposed model is 97.02%, and the recall is 97.60%. It explains that the model can detect Web attack requests effectively. Simultaneously, the model can label attack payload visually and make the model “interpretable.”

20 October 2025 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
Yijia XuYijia Xu
Yijia Xu
QZQiang Zhang
Qiang Zhang
KWKaiyang Wang
Kaiyang Wang
ZLZhonglin Liu
Zhonglin Liu
CHCHENG HUANG
CHENG HUANG
YFYong Fang
Yong Fang
Web page tampering detection is crucial in web threat perception. Current methods rely on monitoring historical changes of web pages to identify anomalies. These approaches often struggle to effectively distinguish between tampering and benign changes, especially in the presence of numerous dynamic pages. Furthermore, the increasing complexity of website structures places more resource demands on tampering monitoring and makes some malicious alterations more covert and challenging to detect. We propose a web page tampering detection based on pretraining with dynamic temporal graphs. The core of the method involves constructing a website temporal graph model based on evolutionary information, and enhances the graph feature perturbations to expose concealed tampering behaviors. Specifically, the framework's autoencoder is composed of enhanced DySAT, enabling it to handle dynamic data. We introduce DySAT, bolstered with GATv2, to capture dynamic attention. Additionally, we design a temporal masking mechanism and prediction error to improve the effectiveness of generative self-supervised learning in temporal graph pretraining. Experimental results on Webpage Tampering Dataset (WPT-Dataset) demonstrate that our method outperforms other comparative approaches in terms of both detection efficacy and stability. Furthermore, the research findings on the anomaly detector and model performance provide direction for the practical application of our method.