YWYueming Wu

Yueming Wu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yueming Wu has a total of 86 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Reachability Is Only the Beginning: Toward Effect-Aware Vulnerability Analysis for AI Agents

    by Yu Ji, Yang Wei, Yueming Wu, Deqing Zou

    AI agents increasingly rely on tools built on or dependent on open source software (OSS) to access data, invoke services, and modify external resources. Vulnerabilities in these dependencies can there- fore propagate into agent systems. Conventional analyses trace vulnerability effects through explicit program states and data or control dependencies. Agent systems introduce model inference be- tween tool output and subsequent action, so affected states become model-visible observations whose influence depends on semantic interpretation. Program analysis can show that such values reach model input, but not whether they change the generated action or external system. We assess three successive links in this process. Vulnerable execution must change the observation, the changed observation must influence the generated action, and the executed action must change an external resource. Our framework combines program tracing, repeated executions under matched contexts, and external state verification to establish these links.

  • Building global sample graph for effective code clone detection

    by Chaofan Li, Tongyang Xu, Shihan Dou, Jingyuan Li, Ju Jia, Yueming Wu, Deqing Zou

  • Distributed Race Condition Detection in CPSS via Proactive DAG-Guided Hidden Markov Models

    by Hongyi Zhao, Zhen Li, Yueming Wu, Deqing Zou

    Modern cyber-physical-social systems (CPSS) increasingly rely on distributed cloud computing infrastructures to process massive, heterogeneous data streams. However, this architectural convergence introduces critical security challenges, with transient race conditions emerging as a persistent and elusive threat in these highly concurrent, distributed backends. To address this critical bottleneck, we propose a novel distributed intelligence framework for dynamic race condition detection. Our approach consists of: 1) a preprocessing module that utilizes directed acyclic graph (DAG)-based modeling to establish strict causal dependencies and filter concurrent event pairs; and 2) an active detection module that implements granular proactive scheduling to deterministically trigger race-prone interleavings. By integrating hidden Markov models (HMMs) for behavioral anomaly detection, our framework effectively identifies subtle concurrency issues in CPSS-based cloud environments. We validated our method on a curated dataset of 32 verified real-world vulnerabilities across six widely used distributed systems—Apache Hadoop2/Yarn, HDFS, HBase, Cassandra, Zookeeper, and Flink. Experimental results demonstrate that our approach achieves a 75.0% detection rate, significantly outperforming traditional fuzzing and static baselines ($\boldsymbol{p} \mathbf{\lt 0.01}$). Crucially, the framework maintains a statistically manageable low-latency runtime overhead (12.3%), offering an acceptable trade-off between detection rate and system efficiency. By transforming transient concurrent flaws into consistently reproducible vulnerabilities, this approach substantially enhances the security, reliability, and trust foundations necessary for the robust deployment of modern CPSS architectures.

  • Open Access

    VulInject: Multi-Type Samples Generation for Learning-based Vulnerability Detection

    by Yumeng Wu, Zhen Li, Zhuoyuan Li, Zhiyuan Yang, Yueming Wu, Deqing Zou, Hai Jin

    Deep learning-based source code vulnerability analysis has become a prominent trend in vulnerability detection, offering the capability to automatically extract vulnerability features and reduce manual effort. However, the limited availability of vulnerability data prevents models from comprehensively capturing diverse vulnerability patterns. In addition, the scarcity of samples labeled with specific vulnerability types restricts models to merely identifying the presence of vulnerabilities, without providing fine-grained type information that is crucial for efficient vulnerability diagnosis and remediation. To address these challenges, we propose VulInject, the first automated tool for generating multi-type vulnerable samples for learning-based detection. Our approach extracts edit patterns from existing vulnerability datasets and applies them to benign projects, thereby synthesizing realistic vulnerable code resembling real-world cases. Furthermore, we adopt a hybrid strategy that integrates static analysis with large language models to annotate the generated samples with precise vulnerability types. By augmenting existing datasets with these generated samples, we conduct extensive experiments on state-of-the-art binary and multi-class vulnerability detection models. Results demonstrate substantial performance gains, with binary classification models achieving up to a 13.50% increase in F1 score, and multi-class models improving by 7.65%.

  • Exploring Neural Network Structure Code Reuse in the Open‐Source Community for Improving Maintenance

    by Xiaoning Ren, Yuekun Wang, Chongyang Liu, Yueming Wu, Qiang Hu, Lijun Zhang, Yinxing Xue

    Neural networks (NNs) have rapidly advanced, demonstrating exceptional performance across various fields, leading to a surge in open‐source NN projects. The complexity and rapid growth of these projects pose significant challenges for maintenance within the open‐source community. Given that NN architecture code is the core asset of NN projects, understanding its reuse in the open‐source community is essential for effective maintenance, such as reducing redundancy and identifying potential intellectual property violations. While prior studies have examined code reuse in open‐source projects, they have two key limitations: They do not specifically address NN structure code, and they rely on manually selected small‐scale datasets that do not sufficiently represent the broader open‐source ecosystem. To address these limitations, this study explores reuse patterns in a large‐scale dataset of 20,000 open‐source projects on GitHub, focusing specifically on NN structure code. Specially, we categorize NN structure reuse into three types: (1) exact reuse with no changes; (2) shallow reuse with minor adjustments like renaming variables or adjusting parameters; and (3) conceptual reuse with significant modifications, while retaining the same layer sequence. We then propose a detection framework, NNReuse , to identify these reuse types and conduct an empirical evaluation of their prevalence and characteristics. As a practical application, we also assess potential license conflicts based on NNReuse . Extensive experiments show that 55.6% of projects and 54.17% of NN structures exhibit structural similarities that are consistent with potential NN structure reuse in open‐source projects. Among these, exact reuse is particularly common and introduces significant redundancy, with an estimated storage optimization potential of up to 34.49%. Reuse primarily occurs at a high level, with 43.3% involving the reuse of overall network architecture. Additionally, in projects with license protection, as much as 64.3% may present potential license conflicts, highlighting the importance of strengthened license compliance and proactive IP risk mitigation in the open‐source community.

  • Open Access

    Seeking Certainty from Uncertainty: A Training Framework for Android Malware Detection Resilient to Label Noise

    by Cuiying Gao, Hanwen Zhang, Heng Li, Wei Zhou, Haolan Zhang, Yueming Wu, Wei Yuan, Yang Liu

    The high-quality labeled dataset is crucial for building effective Android malware detection models. However, widely used automated labeling systems (e.g., antivirus services) are often not stable enough and may introduce label noise. In this paper, we identify and analyze two types of noise: RDMnoise and IDNnoise . RDMnoise is introduced by the labeling system randomly flipping labels, exhibiting class symmetry. In contrast, IDNnoise arises primarily because engines tend to misclassify obfuscated software as malware, exhibiting class dependency. Both types of noise can bias the training process of malware detection systems, thereby affecting the overall performance of the model. To combat these two types of noise of Android malware detection, we propose a lightweight training framework called CoNoMAD , which combines model-level and data-level approaches to jointly mitigate label noise. Specifically, to overcome the uncertainty introduced by noisy labels for model training, we assist the training by seeking more certainty in the supervisory information from both the model and data levels. On the model level, CoNoMAD relies on an under-trained model. The intuition behind this is to reduce the model's sensitivity to noisy labels by limiting its capacity to overfit. On the data level, CoNoMAD employs a clustering algorithm to mitigate the impact of noise on data distribution by identifying and grouping similar data points. Through auxiliary training on these two levels, CoNoMAD effectively mitigates the negative impact of label noise on models in complex scenarios. We validate the performance of CoNoMAD on 25 datasets with varying noise ratios, including the RDMnoise dataset, the IDNnoise dataset, and a mixed dataset containing both types of noise. Experiments show CoNoMAD improves detection performance by 50.89%, 24.30%, and 29.34% on popular malware detectors, under the RDMnoise , IDNnoise , and Mixed Noise. Compared to state-of-the-art methods, CoNoMAD achieves higher detection performance and training efficiency. Finally, this study calls for more attention to the impact of label noise on Android malware detection.


  • Open Access

    VulDeNoise: Outlier Detection to Reduce Label Noises for Effective Vulnerability Detection

    by Yutao Hu, Suyuan Wang, Yu Ji, Yueming Wu, Deqing Zou

    While automated vulnerability detection approaches, especially those using Graph Neural Networks (GNNs), have shown remarkable promise, their effectiveness is often constrained by significant label noise in prevalent vulnerability datasets. To address this, we propose VulDeNoise , an innovative dataset denoising framework. Our approach is grounded in multi-view learning theory, postulating that correctly labeled samples exhibit consistent training dynamics across different code graph representations, whereas mislabeled samples manifest significant discrepancies due to inherent semantic conflicts. VulDenoise operationalizes this by training a target detector on each of the three code representation graphs, constructing a loss vector for each sample from its cross-view training loss sequences, and then employing an ensemble of outlier detection algorithms to find noisy instances. We conducted extensive experiments on four prominent GNN-based detectors ( Devign , DeepWukong , ReVEAL , and IVDetect ) using the Big-Vul and FFmpeg+QEMU datasets. The results demonstrate that training on Big-Vul dataset denoised by VulDeNoise consistently enhances the F1-score of these four detectors by 5-10%. In controlled experiments on the FFmpeg+QEMU dataset, where label noise was synthetically added at varying ratios, VulDeNoise achieved a denoising F1-score of up to 70%, demonstrating its high effectiveness in identifying noisy labels. Furthermore, VulDeNoise substantially outperforms state-of-the-art denoising methods like Confident Learning and Differential Training , and even surpasses a Large Language Model (LLM)-based auditing approach. Ablation studies confirm the robustness of our design, revealing that the synergy of all three code representations and a carefully selected training duration are essential for optimal performance. VulDeNoise offers an effective, automated solution for improving the quality of vulnerability datasets, paving the way for more reliable deep learning-based vulnerability detection models.

  • Eler: Ensemble Learning-Based Automated Verification of Code Clones

    by Shihan Dou, Yutao Hu, Siyue Feng, Yueming Wu, Deqing Zou

    The clone detection of source code is the inspection of software for the presence of similar code fragments. The evaluation of clone detection techniques is crucial for the development of software engineering. An accurate assessment of the effectiveness of clone detection algorithms necessitates the meticulous verification of whether the clone pairs identified by the algorithm under evaluation are indeed authentic clone pairs. However, manual verification of the accuracy of claimed clones by human experts is often an extremely time-consuming and labour-intensive task. In this paper, we introduce Eler, a new automated high-precision clone verification approach leveraging ensemble learning techniques. In particular, we employ various clone detection algorithms based on distinct code representations to extract features. Subsequently, we apply a combination of machine learning techniques and ensemble learning to these features. Eler can achieve the verification of clones with 95% precision while being able to reduce manual labour by 84.75%. It performs better than the most advanced code cloning verification techniques available (87.4% of CloneCognition and 89.5% of InspectorClone in precision).

  • Open Access

    A Scalable Vulnerability Detection System with Multi-View Graph Representations

    by Shihan Dou, Huiyuan Zheng, Junjie Shan, Yueming Wu, Deqing Zou, Xuanjing Huang, Yang Liu

    Deep learning (DL) has been extensively utilized in source code vulnerability detection due to its robust automatic feature extraction capabilities. To achieve scalable vulnerability scanning, some prior studies intend to process the source code directly by treating them as text. However, these text-based methods can not achieve the best performance due to the lack utilizing program semantics. In contrast, other approaches aim to enhance accuracy by distilling program semantics into graph representations for vulnerability detection. Despite their accuracy, these graph-based methods are not scalable, as graph analysis is generally time-intensive. In this paper, we aim to achieve both scalability and accuracy in scanning large-scale source code vulnerabilities. Inspired by existing DL-based image classification which has the ability to analyze millions of images accurately, we prefer to use these techniques to accomplish our purpose. Specifically, we propose an innovative approach that efficiently converts the source code of a function into multi-view images, while preserving the diverse program information from different perspectives. Based on this approach, we introduce a vulnerability detection system, VulCNN , which can leverage the function images and simple convolutional neural networks (CNN) to effectively and efficiently detect vulnerabilities. We implement VulCNN and evaluate it on three popular and widely used datasets ( ie., the Devign , Big-Vul , and ReVeal datasets). Experimental results report that VulCNN can achieve better accuracy than nine state-of-the-art vulnerability detectors ( ie., TokenCNN , VulDeePecker , SySeVR , VulDeeLocator , Devign , EPVD , VulDecgre , UniXcoder , and PDBERT ). We also compare VulCNN with three widely used Large Language Models ( ie., Llama-2-Instruct , DeepSeek-Coder , Qwen2.5-Coder-Instruct ) and one LLM-based detection method ( ie., GRACE ), and the experimental results demonstrate that our proposed method can perform better than most of vulnerability detection methods. As for scalability, VulCNN is about five times faster than VulDeeLocator , and about two times faster than Devign . VulCNN achieves vulnerability detection effectiveness comparable to the state-of-the-art method GRACE , but with a 31.52% reduction in time overhead.