Pengbin Feng

Dr. Pengbin Feng


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
6 June 2018 in IEEE Access
Verified
Journal Article
Open access
PFPengbin Feng
Pengbin Feng
JMJianfeng Ma
Jianfeng Ma
CSCong Sun
Cong Sun
XXXinpeng Xu
Xinpeng Xu
YMYuwan Ma
Yuwan Ma
With the popularity of Android smartphones, malicious applications targeted Android platform have explosively increased. Proposing effective Android malware detection method for preventing the spread of malware has become an emerging issue. Various features extracted through static and dynamic analysis in conjunction with machine learning algorithm have been the mainstream in large-scale malware identification. In general, static analysis becomes invalid in detecting applications which adopt sophisticated obfuscation techniques like encryption or dynamic code loading. However, dynamic analysis is suitable to deal with these evasion techniques. In this paper, we propose an effective dynamic analysis framework, called EnDroid, in the aim of implementing highly precise malware detection based on multiple types of dynamic behavior features. These features cover system-level behavior trace and common application-level malicious behaviors like personal information stealing, premium service subscription, malicious service communication. In addition, EnDroid adopts feature selection algorithm to remove noisy or irrelevant features and extracts critical behavior features. Extracting behavior features through runtime monitor, EnDroid is able to distinguish malicious from benign applications with ensemble learning algorithm. Through experiments, we prove the effectiveness of EnDroid on two datasets. Furthermore, we find Stacking achieves the best classification performance and is promising in Android malware detection.

4 June 2021 in Mobile Information Systems
Verified
Journal Article
Open access
PDF file
PFPengbin Feng
Pengbin Feng
JMJianfeng Ma
Jianfeng Ma
TLTeng Li
Teng Li
XMXindi Ma
Xindi Ma
NXNing Xi
Ning Xi
DLDi Lu
Di Lu
With the widespread usage of Android smartphones in our daily lives, the Android platform has become an attractive target for malware authors. There is an urgent need for developing an automatic malware detection approach to prevent the spread of malware. The low code coverage and poor efficiency of the dynamic analysis limit the large-scale deployment of malware detection methods based on dynamic features. Therefore, researchers have proposed a plethora of detection approaches based on abundant static features to provide efficient malware detection. This paper explores the direction of Android malware detection based on graph representation learning. Without complex feature graph construction, we propose a new Android malware detection approach based on lightweight static analysis via the graph neural network (GNN). Instead of directly extracting Application Programming Interface (API) call information, we further analyze the source code of Android applications to extract high-level semantic information, which increases the barrier of evading detection. Particularly, we construct approximate call graphs from function invocation relationships within an Android application to represent this application and further extract intrafunction attributes, including required permission, security level, and Smali instructions’ semantic information via Word2Vec, to form the node attributes within graph structures. Then, we use the graph neural network to generate a vector representation of the application, and then malware detection is performed on this representation space. We conduct experiments on real-world application samples. The experimental results demonstrate that our approach implements high effective malware detection and outperforms state-of-the-art detection approaches.

17 April 2023 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
PFPengbin Feng
Pengbin Feng
LYLi Yang
Li Yang
Di LuDi Lu
Di Lu
Ning XiNing Xi
Ning Xi
JMJianfeng Ma
Jianfeng Ma

4 October 2021
Verified
Conference Paper
Closed access
SLSongsong Liu
Songsong Liu
PFPengbin Feng
Pengbin Feng
KSKun Sun
Kun Sun
Web server is an appealing target for attackers since it may be exploited to gain access to an organization’s internal network. After compromising a web server, the attacker can construct a webshell to maintain a long-term and stealthy access for further attacks. Among all webshell-based attacks, command injection is a powerful attack that can be launched to steal sensitive data from the web server or compromising other computers in the network. To monitor and analyze webshell-based command injection, we develop a hybrid webshell honeypot framework called HoneyBog, which intercepts and redirects malicious injected commands from the front-end honeypot to the high-fidelity back-end honeypot for execution. HoneyBog can achieve two advantages by using the client-server honeypot architecture. First, since the webshell-based injected commands are transferred from the compromised web server to a remote constrained execution environment, we can prevent the attacker from launching further attacks in the protected network. Second, it facilitates the centralized management of high-fidelity honeypots for remote honeypot service providers. Moreover, we increase the system fidelity of HoneyBog by synchronizing the website files between the front-end and back-end honeypots. We implement a prototype of HoneyBog using PHP and the Apache web server. Our experiments on 260 PHP webshells show that HoneyBog can effectively intercept and redirect injected commands with a low performance overhead.

11 June 2025 in Electronics
Verified
Journal Article
Open access
PDF file
YXYongcai Xiao
Yongcai Xiao
JXJian Xu
Jian Xu
ZLZejian Lin
Zejian Lin
YXYaxuan Xie
Yaxuan Xie
RLRuitong Liu
Ruitong Liu
PFPengbin Feng
Pengbin Feng
With the growing scale and complexity of smart grids, ensuring both effective anomaly detection and robust privacy protection has become increasingly critical. This paper proposes a ciphertext-based anomaly detection model built upon a collaborative architecture between edge computing and public cloud, integrating a hybrid homomorphic encryption scheme that combines partial homomorphic encryption (PHE) and fully homomorphic encryption over torus (TFHE). The encryption method is selected based on the task type: TFHE is used for complex anomaly detection tasks requiring encrypted computation in the cloud, while PHE is applied to cross-regional data aggregation tasks for secure homomorphic addition. Edge nodes handle low-latency, lightweight tasks locally, whereas complex encrypted tasks are processed in the cloud using an enhanced Isolation Forest model adapted for homomorphic computation. Extensive experiments on three benchmark datasets demonstrate that the proposed model achieves anomaly detection performance comparable to plaintext-based models, while significantly outperforming existing homomorphic encryption-based methods in terms of accuracy and ROC-AUC. This work provides a scalable and practical solution for secure and efficient anomaly detection in smart grids.

30 April 2017 in Mobile Information Systems
Verified
Journal Article
Open access
PDF file
PFPengbin Feng
Pengbin Feng
JMJianfeng Ma
Jianfeng Ma
CSCong Sun
Cong Sun
Nowadays, mobile devices are widely used to store and process user privacy and confidential data. With the popularity of Android platform, the cases of attacks against users’ privacy-sensitive data within Android applications are on the rise. Researchers have developed sophisticated static and dynamic analysis tools to detect information leakage. These methods cannot distinguish legitimate usage of sensitive data in benign apps from the intentional sensitive data leakages in malicious apps. Recently, malicious apps have been found to treat sensitive data differently from benign apps. These differences can be used to flag malicious apps based on their abnormal data flows. In this paper, we further find that some sensitive data flows show great difference between benign apps and malware. We can use these differences to select critical data flows. These critical flows can guide the identification of malware based on the abnormal usage of sensitive data. We present SCDFLOW, a tool that automatically selects critical data flows within Android applications and takes these critical flows as feature for abnormal behavior detection. Compared with MUDFLOW, SCDFLOW increases the true positive rate of malware detection by 5.73%~9.07% on different datasets and causes an ignorable effect on memory consumption.