Wenhan Zhu

Wenhan Zhu

Auto-generated profile, based on publicly available information

Wenhan Zhu

Huawei, Markham, Canada

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
6 August 2022 in Empirical Software Engineering
Verified
Journal Article
Closed access
PDF file
WZWenhan Zhu
Wenhan Zhu
HZHaoxiang Zhang
Haoxiang Zhang
AHAhmed E. Hassan
Ahmed E. Hassan
MGMichael W. Godfrey
Michael W. Godfrey

19 June 2025 in Proceedings of the ACM on Software Engineering
Verified
Journal Article
Open access
XYXu Yang
Xu Yang
WZWenhan Zhu
Wenhan Zhu
MPMichael Pacheco
Michael Pacheco
JZJiayuan Zhou
Jiayuan Zhou
SWShaowei Wang
Shaowei Wang
KLKui Liu
Kui Liu
Detecting vulnerability fix commits in open-source software is crucial for maintaining software security. To help OSS identify vulnerability fix commits, several automated approaches are developed. However, existing approaches like VulFixMiner and CoLeFunDa, focus solely on code changes, neglecting essential context from development artifacts. Tools like Vulcurator, which integrates issue reports, fail to leverage semantic associations between different development artifacts (e.g., pull requests and history vulnerability fixes). Moreover, they miss vulnerability fixes in tangled commits and lack explanations, limiting practical use. Hence to address those limitations, we propose LLM4VFD, a novel framework that leverages Large Language Models (LLMs) enhanced with Chain-of-Thought reasoning and In-Context Learning to improve the accuracy of vulnerability fix detection. LLM4VFD comprises three components: (1) Code Change Intention, which analyzes commit summaries, purposes, and implications using Chain-of-Thought reasoning; (2) Development Artifact, which incorporates context from related issue reports and pull requests; (3) Historical Vulnerability, which retrieves similar past vulnerability fixes to enrich context. More importantly, on top of the prediction, LLM4VFD also provides a detailed analysis and explanation to help security experts understand the rationale behind the decision. We evaluated LLM4VFD against state-of-the-art techniques, including Pre-trained Language Model-based approaches and vanilla LLMs, using a newly collected dataset, BigVulFixes. Experimental results demonstrate that LLM4VFD significantly outperforms the best-performed existing approach by 68.1%--145.4%. Furthermore, We conducted a user study with security experts, showing that the analysis generated by LLM4VFD improves the efficiency of vulnerability fix identification.

2 January 2024 in Empirical Software Engineering
Verified
Journal Article
Closed access
PDF file
WZWenhan Zhu
Wenhan Zhu
SPSebastian Proksch
Sebastian Proksch
DGDaniel M. German
Daniel M. German
MGMichael W. Godfrey
Michael W. Godfrey
Li LiLi Li
Li Li
SMShane McIntosh
Shane McIntosh

19 June 2025 in Proceedings of the ACM on Software Engineering
Verified
Journal Article
Open access
XYXu Yang
Xu Yang
SWShaowei Wang
Shaowei Wang
JZJiayuan Zhou
Jiayuan Zhou
WZWenhan Zhu
Wenhan Zhu
Deep Learning-based Vulnerability Detection (DLVD) techniques have garnered significant interest due to their ability to automatically learn vulnerability patterns from previously compromised code. Despite the notable accuracy demonstrated by pioneering tools, the broader application of DLVD methods in real-world scenarios is hindered by significant challenges. A primary issue is the “one-for-all” design, where a single model is trained to handle all types of vulnerabilities. This approach fails to capture the patterns of different vulnerability types, resulting in suboptimal performance, particularly for less common vulnerabilities that are often underrepresented in training datasets. To address these challenges, we propose MoEVD, which adopts the Mixture-of-Experts (MoE) framework for vulnerability detection. MoEVD decomposes vulnerability detection into two tasks, CWE type classification and CWE-specific vulnerability detection. By splitting the task, in vulnerability detection, MoEVD allows specific experts to handle distinct types of vulnerabilities instead of handling all vulnerabilities within one model. Our results show that MoEVD achieves an F1-score of 0.44, significantly outperforming all studied state-of-the-art (SOTA) baselines by at least 12.8%. MoEVD excels across almost all CWE types, improving recall over the best SOTA baseline by 9% to 77.8%. Notably, MoEVD does not sacrifice performance on long-tailed CWE types; instead, its MoE design enhances performance (F1-score) on these by at least 7.3%, addressing long-tailed issues effectively.

1 October 2026 in Proceedings of the ACM on Software Engineering
Verified
Journal Article
Open access
XYXu Yang
Xu Yang
JZJiayuan Zhou
Jiayuan Zhou
MPMichael Pacheco
Michael Pacheco
WZWenhan Zhu
Wenhan Zhu
PHPengfei He
Pengfei He
RPRuiqi Pan
Ruiqi Pan
Driven by the advancements of Large Language Models (LLMs), LLM-powered agents are making significant improvements in software engineering tasks, yet struggle with complex, repository-level issue resolution. Existing agent-based methods have two key limitations. First, they lack of procedural knowledge (i.e., how an issue is fixed step-by-step and rationales behind it) to learn and leverage for issue resolution. Second, they rely on massive computational power to blindly explore the solution space. To address those limitations, we propose Lingxi, an issue resolution framework that leverages procedural knowledge extracted from historical issue-fixing data to guide agents in solving repository-level issues. Lingxi first constructs this knowledge offline through a hierarchical abstraction mechanism, enabling agents to learn the how and why behind a fix, not just the final solution. During online application, it employs a knowledge-driven scaling method that leverages the procedural knowledge of similar issues to intelligently analyze the target issue from multiple perspectives, in sharp contrast to undirected, brute-force exploration.Lingxi successfully resolves 74.6% of bugs on the SWE-bench Verified benchmark in Pass@1 setting, outperforming five state-of-the-art techniques by a significant margin (5.4% to 14.9%). Our comprehensive ablation study confirmed that the success of Lingxi comes directly from its use of procedural knowledge. Without it, the performance gains from scaling alone is negligible. Our qualitative study further shows that the “design patterns & coding practices” is the most critical knowledge aspect, and that the roles of different knowledge aspects switch across different stages (i.e., analysis, planning, and fixing).

19 July 2022 in arXiv
Verified
Preprint
Open access
PDF file
WZWenhan Zhu
Wenhan Zhu
HZHaoxiang Zhang
Haoxiang Zhang
AHAhmed E. Hassan
Ahmed E. Hassan
MGMichael W. Godfrey
Michael W. Godfrey
Stack Overflow provides a means for developers to exchange knowledge. While much previous research on Stack Overflow has focused on questions and answers (Q&A), recent work has shown that discussions in comments also contain rich information. On Stack Overflow, discussions through comments and chat rooms can be tied to questions or answers. In this paper, we conduct an empirical study that focuses on the nature of question discussions. We observe that: (1) Question discussions occur at all phases of the Q&A process, with most beginning before the first answer is received. (2) Both askers and answerers actively participate in question discussions; the likelihood of their participation increases as the number of comments increases. (3) There is a strong correlation between the number of question comments and the question answering time (i.e., more discussed questions receive answers more slowly); also, questions with a small number of comments are likely to be answered more quickly than questions with no discussion. Our findings suggest that question discussions contain a rich trove of data that is integral to the Q&A processes on Stack Overflow. We further suggest how future research can leverage the information in question discussions, along with the commonly studied Q&A information.