Selected work

Representative Papers

Synthetic Network Packet Generation through Statistical Learning and Genetic Algorithms

Jun 18, 2026

This study addresses the limitations of existing IoT intrusion detection datasets, which commonly suffer from fixed attack categories and extreme class imbalance, as well as the inability of current generative models to guarantee the physical validity of synthesized packets. To overcome these challenges, the paper proposes two novel synthesis approaches that embed hard validity constraints directly into the generation process: a statistical learning method based on PCA and dual anomaly detection boundaries, and a genetic algorithm that formulates data generation as a multi-objective optimization problem. Innovatively integrating dual anomaly gating, feature-range clamping, and an independent validation mechanism, both methods significantly enhance the fidelity and validity of synthetic data. Evaluated on the ACI IoT 2023 dataset, they achieve average anomaly rates of 1.20% (at 1,091 pkt/s) and 0.62% (at 5.7 pkt/s), respectively, and successfully expand ARP spoofing samples to 1,000 instances—a 200-fold increase.

0 citationsRead paper

Categorical Robustness Assessment for Machine Learning based Network Intrusion Detection Systems

Jun 10, 2026

This study addresses the lack of systematic evaluation of model robustness in existing network intrusion detection systems under adversarial attacks. Within a unified framework and using the ACI-IoT-2023 dataset, the authors conduct a cross-architecture and cross-attack robustness comparison of 1D CNN, LSTM, and Random Forest models against FGSM and PGD attacks with perturbation budgets ε ∈ [0.01, 0.1]. The findings reveal that high baseline accuracy does not guarantee strong adversarial robustness: although Random Forest achieves 99.98% accuracy under benign conditions, its performance drops by 73 percentage points under minimal perturbations. In contrast, the 1D CNN demonstrates superior robustness, maintaining 95.5% accuracy at ε = 0.01 with gradual degradation. This work is the first to systematically uncover disparities in adversarial vulnerability among mainstream models in normalized feature spaces, offering critical insights for real-world deployment.

0 citationsRead paper

A Knowledge-Driven LLM-Based Decision-Support System for Explainable Defect Analysis and Mitigation Guidance in Laser Powder Bed Fusion

May 01, 2026

This study addresses the challenges of defect diagnosis, limited interpretability, and insufficient mitigation guidance in laser powder bed fusion (LPBF) manufacturing by proposing a decision support system that integrates a structured defect ontology with a large language model (LLM). The system enables natural language querying, provides explanations of defect root causes, and recommends mitigation strategies, while incorporating a vision–language model to semantically interpret microstructural defects. Innovatively, it employs an ontology-driven knowledge representation framework coupled with a semantic alignment scoring mechanism to facilitate joint visual–textual reasoning and causal modeling. Evaluated on a literature-derived dataset, the approach achieves a macro-averaged F1 score of 0.808, and Cohen’s kappa indicates substantial agreement between model outputs and expert annotations, significantly outperforming baseline methods.

0 citationsRead paper

VulStyle: A Multi-Modal Pre-Training for Code Stylometry-Augmented Vulnerability Detection

Apr 29, 2026

This work proposes VulStyle, a novel approach to vulnerability detection that addresses two key limitations of existing methods: the neglect of risk-prone programming habits implicit in code style and the structural complexity introduced by full abstract syntax trees (ASTs). VulStyle is the first to incorporate code style (CStyle) as an auxiliary signal for vulnerability detection, integrating function-level source code, a pruned non-terminal AST, and stylistic features within a multimodal pre-training framework. This design preserves semantic hierarchy while reducing structural complexity and enables cross-language transferability. Experimental results demonstrate that VulStyle achieves F1 score improvements of 4%–48% over prior methods on the BigVul and VulDeePecker benchmarks and attains state-of-the-art or best average performance across five standard datasets.

0 citationsRead paper

Insights into Security-Related AI-Generated Pull Requests

Apr 21, 2026

This study investigates the security implications of AI-powered coding agents, which, while enhancing developer productivity, may introduce vulnerabilities and exhibit distinct code review behaviors compared to human developers. Analyzing 675 security-related pull requests (PRs) drawn from over 33,000 AI-generated PRs, the work employs large-scale data mining, vulnerability categorization, and qualitative content analysis to characterize recurrent defect patterns in AI-generated secure code—such as inefficient regular expressions, injection flaws, and path traversal vulnerabilities. It extends existing PR rejection taxonomies to accommodate AI contributions and uncovers the significant influence of procedural and social factors on the acceptance of AI-generated code. Notably, many defective PRs are still merged, with rejections primarily driven by process-related issues rather than code quality, and submission metadata shows limited impact on acceptance rates.

0 citationsRead paper

Recent publications

Latest Papers

Synthetic Network Packet Generation through Statistical Learning and Genetic Algorithms

Jun 18, 2026

This study addresses the limitations of existing IoT intrusion detection datasets, which commonly suffer from fixed attack categories and extreme class imbalance, as well as the inability of current generative models to guarantee the physical validity of synthesized packets. To overcome these challenges, the paper proposes two novel synthesis approaches that embed hard validity constraints directly into the generation process: a statistical learning method based on PCA and dual anomaly detection boundaries, and a genetic algorithm that formulates data generation as a multi-objective optimization problem. Innovatively integrating dual anomaly gating, feature-range clamping, and an independent validation mechanism, both methods significantly enhance the fidelity and validity of synthetic data. Evaluated on the ACI IoT 2023 dataset, they achieve average anomaly rates of 1.20% (at 1,091 pkt/s) and 0.62% (at 5.7 pkt/s), respectively, and successfully expand ARP spoofing samples to 1,000 instances—a 200-fold increase.

0 citationsRead paper

Categorical Robustness Assessment for Machine Learning based Network Intrusion Detection Systems

Jun 10, 2026

This study addresses the lack of systematic evaluation of model robustness in existing network intrusion detection systems under adversarial attacks. Within a unified framework and using the ACI-IoT-2023 dataset, the authors conduct a cross-architecture and cross-attack robustness comparison of 1D CNN, LSTM, and Random Forest models against FGSM and PGD attacks with perturbation budgets ε ∈ [0.01, 0.1]. The findings reveal that high baseline accuracy does not guarantee strong adversarial robustness: although Random Forest achieves 99.98% accuracy under benign conditions, its performance drops by 73 percentage points under minimal perturbations. In contrast, the 1D CNN demonstrates superior robustness, maintaining 95.5% accuracy at ε = 0.01 with gradual degradation. This work is the first to systematically uncover disparities in adversarial vulnerability among mainstream models in normalized feature spaces, offering critical insights for real-world deployment.

0 citationsRead paper

A Knowledge-Driven LLM-Based Decision-Support System for Explainable Defect Analysis and Mitigation Guidance in Laser Powder Bed Fusion

May 01, 2026

This study addresses the challenges of defect diagnosis, limited interpretability, and insufficient mitigation guidance in laser powder bed fusion (LPBF) manufacturing by proposing a decision support system that integrates a structured defect ontology with a large language model (LLM). The system enables natural language querying, provides explanations of defect root causes, and recommends mitigation strategies, while incorporating a vision–language model to semantically interpret microstructural defects. Innovatively, it employs an ontology-driven knowledge representation framework coupled with a semantic alignment scoring mechanism to facilitate joint visual–textual reasoning and causal modeling. Evaluated on a literature-derived dataset, the approach achieves a macro-averaged F1 score of 0.808, and Cohen’s kappa indicates substantial agreement between model outputs and expert annotations, significantly outperforming baseline methods.

0 citationsRead paper

VulStyle: A Multi-Modal Pre-Training for Code Stylometry-Augmented Vulnerability Detection

Apr 29, 2026

This work proposes VulStyle, a novel approach to vulnerability detection that addresses two key limitations of existing methods: the neglect of risk-prone programming habits implicit in code style and the structural complexity introduced by full abstract syntax trees (ASTs). VulStyle is the first to incorporate code style (CStyle) as an auxiliary signal for vulnerability detection, integrating function-level source code, a pruned non-terminal AST, and stylistic features within a multimodal pre-training framework. This design preserves semantic hierarchy while reducing structural complexity and enables cross-language transferability. Experimental results demonstrate that VulStyle achieves F1 score improvements of 4%–48% over prior methods on the BigVul and VulDeePecker benchmarks and attains state-of-the-art or best average performance across five standard datasets.

0 citationsRead paper

Insights into Security-Related AI-Generated Pull Requests

Apr 21, 2026

This study investigates the security implications of AI-powered coding agents, which, while enhancing developer productivity, may introduce vulnerabilities and exhibit distinct code review behaviors compared to human developers. Analyzing 675 security-related pull requests (PRs) drawn from over 33,000 AI-generated PRs, the work employs large-scale data mining, vulnerability categorization, and qualitative content analysis to characterize recurrent defect patterns in AI-generated secure code—such as inefficient regular expressions, injection flaws, and path traversal vulnerabilities. It extends existing PR rejection taxonomies to accommodate AI contributions and uncovers the significant influence of procedural and social factors on the acceptance of AI-generated code. Notably, many defective PRs are still merged, with rejections primarily driven by process-related issues rather than code quality, and submission metadata shows limited impact on acceptance rates.

0 citationsRead paper