arXiv subjects

Duc-Ly Vu

Publications and source records attributed to Duc-Ly Vu.

6 recordsLinked to original sources

arXiv2026

Taint-Based Code Slicing for LLMs-based Malicious NPM Package Detection

Software supply chain attacks on the npm ecosystem have grown increasingly sophisticated, exploiting obfuscation and complex logic to evade detection. Large Language Models (LLMs) offer strong semantic understanding of code but face practical constraints: limited context windows and high inference costs make full-package analysis infeasible, while naive token-based splitting fragments semantic context and degrades accuracy. This paper introduces an LLM-based framework for malicious npm package detection built on code-slicing techniques. We propose an adaptation of taint-based slicing for the npm ecosystem, guided by a curated inventory of JavaScript-specific sensitive APIs, to isolate security-relevant data flows from benign boilerplate. The approach reduces the mean input token count by 99.75% and the median by 93.7% while preserving critical malicious behaviors. Packages relying on dynamic code generation or obfuscation yield empty slices under static analysis and require deobfuscation preprocessing, a limitation we explicitly discuss. The framework is evaluated on a dataset of more than 7000 malicious and benign npm packages using DeepSeek-Coder6.7B. On the 2537 packages amenable to static taint analysis, taint-based slicing achieves 87.04% detection accuracy, outperforming both a naive token-splitting baseline at 75.41% and a CFG-only static slicing approach at 75.65%. These results demonstrate that semantically targeted input representations improve LLM-based detection performance beyond what is achievable through simple input-size reduction, providing an effective and computationally practical defense against evolving open-source supply-chain threats.

cs.CR↗

arXiv2026

Pack-A-Mal: A Malware Analysis Framework for Open-Source Packages

The increasingly sophisticated environment in which attackers operate makes software security an even greater challenge in open-source projects, where malicious packages are prevalent. Static analysis tools, such as Malcontent, are highly useful but are often incapable of dealing with obfuscated malware. Such situations lead to an unreasonably high rate of false positives. This paper highlights that dynamic analysis, rather than static analysis, provides greater insight but is also more resource-intensive for understanding software behaviour during execution. In this study, we enhance a dynamic analysis tool, package-analysis, to capture key runtime behaviours, including commands executed, files accessed, and network communications. This modification enables the use of container sandboxing technologies, such as gVisor, to analyse potentially malicious packages without significantly compromising the host system.

cs.CR↗

arXiv2025

Towards Classifying Benign And Malicious Packages Using Machine Learning

Recently, the number of malicious open-source packages in package repositories has been increasing dramatically. While major security scanners focus on identifying known Common Vulnerabilities and Exposures (CVEs) in open-source packages, there are very few studies on detecting malicious packages. Malicious open-source package detection typically requires static, dynamic analysis, or both. Dynamic analysis is more effective as it can expose a package's behaviors at runtime. However, current dynamic analysis tools (e.g., ossf's package-analysis) lack an automatic method to differentiate malicious packages from benign packages. In this paper, we propose an approach to extract the features from dynamic analysis (e.g., executed commands) and leverage machine learning techniques to automatically classify packages as benign or malicious. Our evaluation of nearly 2000 packages on npm shows that the machine learning classifier achieves an AUC of 0.91 with a false positive rate of nearly 0%.

cs.CR↗

arXiv2025

A Study of Malware Prevention in Linux Distributions

Malicious attacks on open-source software packages are a growing concern. The discovery of the XZ Utils backdoor intensified these concerns because of the potential widespread impact. This study, therefore, explores the challenges of preventing and detecting malware in Linux distribution package repositories. To do so, we ask two research questions: (1) What measures have Linux distributions implemented to counter malware, and how have maintainers experienced these efforts? (2) How effective are current malware detection tools in identifying malicious Linux packages? To answer these questions, we conduct interviews with maintainers at several major Linux distributions and introduce a Linux package malware benchmark dataset. Using this dataset, we evaluate the performance of six open-source malware detection scanners. Distribution maintainers, according to the interviews, have mostly focused on reproducible builds to date. Our interviews identified only a single Linux distribution, Wolfi OS, that performs active malware scanning. Using this new benchmark dataset, the evaluation found that the performance of existing open-source malware scanners is underwhelming. Most studied tools excel at producing false positives but only infrequently detect true malware. Those that avoid high false positive rates often do so at the expense of a satisfactory true positive. Our findings provide insights into Linux distribution package repositories' current practices for malware detection and demonstrate the current inadequacy of open-source tools designed to detect malicious Linux packages.

cs.CR↗

arXiv2022

A Benchmark Comparison of Python Malware Detection Approaches

While attackers often distribute malware to victims via open-source, community-driven package repositories, these repositories do not currently run automated malware detection systems. In this work, we explore the security goals of the repository administrators and the requirements for deployments of such malware scanners via a case study of the Python ecosystem and PyPI repository, which includes interviews with administrators and maintainers. Further, we evaluate existing malware detection techniques for deployment in this setting by creating a benchmark dataset and comparing several existing tools, including the malware checks implemented in PyPI, Bandit4Mal, and OSSGadget's OSS Detect Backdoor. We find that repository administrators have exacting technical demands for such malware detection tools. Specifically, they consider a false positive rate of even 0.01% to be unacceptably high, given the large number of package releases that might trigger false alerts. Measured tools have false positive rates between 15% and 97%; increasing thresholds for detection rules to reduce this rate renders the true positive rate useless. In some cases, these checks emitted alerts more often for benign packages than malicious ones. However, we also find a successful socio-technical malware detection system: external security researchers also perform repository malware scans and report the results to repository administrators. These parties face different incentives and constraints on their time and tooling. We conclude with recommendations for improving detection capabilities and strengthening the collaboration between security researchers and software repository administrators.

cs.CR↗

arXiv2019

A Convolutional Transformation Network for Malware Classification

Modern malware evolves various detection avoidance techniques to bypass the state-of-the-art detection methods. An emerging trend to deal with this issue is the combination of image transformation and machine learning techniques to classify and detect malware. However, existing works in this field only perform simple image transformation methods that limit the accuracy of the detection. In this paper, we introduce a novel approach to classify malware by using a deep network on images transformed from binary samples. In particular, we first develop a novel hybrid image transformation method to convert binaries into color images that convey the binary semantics. The images are trained by a deep convolutional neural network that later classifies the test inputs into benign or malicious categories. Through the extensive experiments, our proposed method surpasses all baselines and achieves 99.14% in terms of accuracy on the testing set.

cs.CR↗