Rui Zheng

Dr. Rui Zheng

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
5 January 2021 in Sensors
Verified
Journal Article
Open access
PDF file
RZRui Zheng
Rui Zheng
HMHao Ma
Hao Ma
QWQiuyun Wang
Qiuyun Wang
JFJianming Fu
Jianming Fu
Zhengwei JiangZhengwei Jiang
Zhengwei Jiang
The network security situation of campus networks on CERNET (China Education and Research Network) has received great concern. However, most network managers have no complete picture of the network security because of its special management and the rapid growth of network assets. In this investigation, the security of campus networks belonging to seven universities in Wuhan was investigated. A tool called “WebHunt” was designed for campus networks, and with its help, the network security risks were found. Differently from existing tools for network probing, WebHunt can adopt the network scale and special rules of the campus network. According to the characteristics of campus websites, a series of functions were integrated into WebHunt, including reverse resolution of domain names, active network detection and fingerprint identification for software assets. Besides, WebHunt builds its vulnerability intelligence database with a knowledge graph structure and locates the vulnerabilities through matching knowledge graph information. Security assessments of seven universities presents WebHunt’s applicability for campus networks. Besides, it also shows that many security risks are concealed in campus networks, such as non-compliance IP addresses and domain names, system vulnerabilities and so on. The security reports containing risks have been sent to the relevant universities, and positive feedback was received.

25 May 2022 in Applied Soft Computing
Verified
Journal Article
Closed access
RZRui Zheng
Rui Zheng
QWQiuyun Wang
Qiuyun Wang
ZLZhuopang Lin
Zhuopang Lin
ZJZhengwei Jiang
Zhengwei Jiang
JFJianming Fu
Jianming Fu
GPGuojun Peng
Guojun Peng

26 March 2022 in Security and Communication Networks
Verified
Journal Article
Open access
PDF file
RZRui Zheng
Rui Zheng
QWQiuyun Wang
Qiuyun Wang
JHJia He
Jia He
JFJianming Fu
Jianming Fu
GSGuga Suri
Guga Suri
Zhengwei JiangZhengwei Jiang
Zhengwei Jiang
Miner malware has been steadily increasing in recent years as the value of cryptocurrency rises, which poses a considerable threat to users’ device security. Miner malware has obvious behavior patterns in order to participate in blockchain computing. However, most miner malware detection methods use raw bytes feature and sequential opcode as detection features. It is difficult for these methods to obtain better detection results due to not modeling robust features. In this paper, a miner malware identification method based on graph classification network is designed by analyzing the features of function call graph and control flow graph of miner malware, called MBGINet. MBGINet can model the behavior graph relationship of miner malware by extracting the connection features of critical nodes in the behavior graph. Finally, MBGINet transforms these node features into the feature vectors of the graph for miner malware identification. In the test experiments, datasets with different volumes are used for simulating real-world scenarios. The experimental results show that the MBGINet method achieves a leading and stable performance compared to the dedicated opcode detection method and obtains an accuracy improvement of 3.08% on the simulated in-the-wild dataset. Meanwhile, MBGINet gains an advantage over the general malware detection method Malconv. These experimental results demonstrate the superiority of the MBGINet method, which has excellent characteristics in adapting to realistic scenarios.

16 February 2026 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
HXHuiyu Xu
Huiyu Xu
WZWenhui Zhang
Wenhui Zhang
ZWZhibo Wang
Zhibo Wang
FXFeng Xiao
Feng Xiao
RZRui Zheng
Rui Zheng
KRKui Ren
Kui Ren
Recently, Large Language Models (LLMs) have been in tegrated into many real-world applications like Code Copilot. These applications have significantly expanded the attack surface of LLMs, ex posing them to complex real-world jailbreak threats. Despite the promising advances in actively finding jailbreak vulnerabilities of LLMs (i.e., red teaming) in general contexts, identifying these threats in complex domain-specific contexts (e.g, mathematical LLMs) remains underexplored. In this paper, we study whether the context these real-world LLM applications work in, including different system prompts, tools, and scenarios of tasks, give rise to context-specific jailbreak threats. Particularly, we adapt general jailbreak prompts to the context of the target application via LLM rewriting to generate context-specific attacks. By measuring the differences in jailbreak responses between general attacks and context-specific attacks, we reveal that customized domain specific LLMs are more vulnerable in their specific context. Motivated by this observation, we propose a context-aware red teaming approach, RedAgent, to generate context-specific jailbreak attacks towards customized LLM applications. Through effectively retrieving and updating structured knowledge in an agent system, RedAgent efficiently perceive and utilize contextual information to adapt the jailbreak prompts to the target contexts. Extensive experiments show that our system can jailbreak most black-box LLMs within just five queries, improving the efficiency of existing red teaming methods by two times. Further, RedAgent can effectively jailbreak customized LLM applications. By generating context-specific jailbreak prompts towards 60 trending applications on the marketplace of OpenAI, we discover 600 vulnerabilities of these real world applications with only two queries per vulnerability.

8 August 2025 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
RZRui Zheng
Rui Zheng
ZWZhibo Wang
Zhibo Wang
KRKui Ren
Kui Ren
CCChun Chen
Chun Chen
Malware remains a major cybersecurity threat, driving increased adoption of machine learning (ML)-based analysis methods. However, these ML solutions face challenges in producing explainable and human-readable results, limiting their practical deployment. Large language models (LLMs) offer a promising alternative for transparent ML malware analysis through analyzing character-level features. Despite this potential, the redundant nature of binary files and ambiguous reasoning patterns pose fundamental challenges in applying LLMs to malware binary analysis. To address these challenges, we propose Anti-Virus Agent (AV-Agent), a framework based on large language models for malware detection. AV-Agent implements a streamlined feature processing pipeline, including multi-layer hierarchical feature classifiers, character feature extraction, and two-phase reasoning. By capturing critical malware features, AV-Agent leverages frontier LLMs’ inherent knowledge to achieve transparent and effective malware analysis. Experimental results on a representative dataset indicate that AV-Agent attains comparable performance to analogous machine learning methods, while also providing an explainable malware analysis process. Additionally, the experiments analyzed the parameter settings of AV-Agent and characteristics of experimental results, demonstrating that AV-Agent achieved optimal performance under the specified parameter conditions while maintaining sufficient stability in malware classification outcomes. These findings demonstrate that LLMs exhibit tremendous potential in human-like reasoning analysis of malware.