Mohamed Mehdi Trigui

Commit messages are essential for understanding software evolution and maintaining traceability of projects; however, their quality varies across repositories. Recent Large Language Models provide a promising path to automate this task by generating concise context-sensitive commit messages directly from code diffs. This paper provides a comparative study of three paradigms of large language models: zero-shot prompting, retrieval-augmented generation, and fine-tuning, using the large-scale CommitBench dataset that spans six programming languages. We assess the performance of the models with automatic metrics, namely BLEU, ROUGE-L, METEOR, and Adequacy, and a human assessment of 100 commits. In the latter, experienced developers rated each generated commit message for Adequacy and Fluency on a five-point Likert scale. The results show that fine-tuning and domain adaptation yield models that perform consistently better than general-purpose baselines across all evaluation metrics, thus generating commit messages with higher semantic adequacy and clearer phrasing than zero-shot approaches. The correlation analysis suggests that the Adequacy and BLEU scores are closer to human judgment, while ROUGE-L and METEOR tend to underestimate the quality in cases where the models generate stylistically diverse or paraphrased outputs. Finally, the study outlines a conceptual integration pathway for incorporating such models into software development workflows, emphasizing a human-in-the-loop approach for quality assurance.

Commit messages are essential for understanding software evolution and maintaining traceability of projects; nevertheless, their quality varies across repositories. Recent Large Language Models provide a promising path to automate this task by generating concise context and sensitive commit messages directly from code diffs. This paper provides a comparative study of three paradigms of large language models: zero-shot prompting, retrieval augmented generation, and fine-tuning, using the large scale CommitBench dataset that spans six programming languages. We assess the performance of the models with automatic metrics, namely BLEU, ROUGE-L, METEOR, and Adequacy, and a human assessment of 100 commits. In the latter, experienced developers rated each generated commit message for Adequacy and Fluency on a five-point Likert scale. The results show that fine-tuning and domain adaptation yield models that perform consistently better than general-purpose baselines across all evaluation metrics, thus generating commit messages with higher semantic adequacy and clearer phrasing than zero-shot. The correlation analysis suggests that the Adequacy and BLEU scores are closer to human judgment, while ROUGE-L and METEOR tend to underestimate the quality in cases where the models generate stylistically diverse or paraphrased outputs. Finally, the study outlines a conceptual integration pathway for incorporating such models into software development workflows, emphasizing a human in the loop approach for quality assurance.

Distributed Denial-of-Service (DDoS) attacks continue to pose significant challenges in Software-Defined Networking (SDN), where the centralized controller often becomes a critical point of failure. As attack strategies grow more advanced, including low-rate and zero-day attacks, there is an increasing need for detection systems that offer both high accuracy and efficient, adaptable performance. In this study, we propose an ensemble-based intrusion detection framework for SDN environments. A central element of the framework is a hybrid feature selection approach that combines Random Forest (RF) feature importance with the Banzhaf Power Index (BPI), a concept from cooperative game theory. This method helps select features that are both relevant and complementary, reducing redundancy and lowering computational demands. The framework incorporates several machine learning models, including XGBoost, Random Forest, Gradient Boosting, Support Vector Machines, k-Nearest Neighbors, AdaBoost, and Naive Bayes. These models are integrated into four ensemble configurations using voting strategies. We evaluate the framework using two datasets: CIC-DDoS2023, which represents recent and diverse attack types, and a flow-based SDN dataset that simulates controller-targeted attacks. The ensemble models showed strong detection performance across both datasets and in many cases, exceeded existing baseline methods. Beyond accuracy, we also analyzed training time, inference latency, memory usage, and model size. One important observation is that resource usage is closely influenced by the number and type of selected features, emphasizing how dataset characteristics impact deployment decisions. While some models trained in under five seconds with very low memory requirements, others required significantly more resources. Overall, the framework offers a practical and effective solution for real-time DDoS detection in SDN systems.

Commit messages are vital for traceability, maintenance, and onboarding in modern software projects, yet their quality is frequently inconsistent. Recent large language models (LLMs) can transform code diffs into natural language summaries, offering a path to more consistent and informative commit messages. This paper makes two contributions: (i) it provides a systematic survey of automated commit message generation with LLMs, critically comparing prompt-only, fine-tuned, and retrieval-augmented approaches; and (ii) it specifies a transparent, agent-based evaluation blueprint centered on CommitBench. Unlike prior reviews, we include a detailed dataset audit, preprocessing impacts, evaluation metrics, and error taxonomy. The protocol defines dataset usage and splits, prompting and context settings, scoring and selection rules, and reporting guidelines (results by project, language, and commit type), along with an error taxonomy to guide qualitative analysis. Importantly, this work emphasizes methodology and design rather than presenting new empirical benchmarking results. The blueprint is intended to support reproducibility and comparability in future studies.