Software-defined network (SDN) is a new approach that allows network control to become directly programmable, and the underlying infrastructure can be abstracted from applications and network services. Control plane). When it comes to security, the centralization that this demands is ripe for a variety of cyber threats that are not typically seen in other network architectures. The authors in this research developed a novel machine-learning method to capture infections in networks. We applied the classifier to the UNSW-NB 15 intrusion detection benchmark and trained a model with this data. Random Forest and Decision Tree are classifiers used to assess with Gradient Boosting and AdaBoost. Out of these best-performing models was Gradient Boosting with an accuracy, recall, and F1 score of 99.87%,100%, and 99.85%, respectively, which makes it reliable in the detection of intrusions for SDN networks. The second best-performing classifier was also a Random Forest with 99.38% of accuracy, followed by Ada Boost and Decision Tree. The research shows that the reason that Gradient Boosting is so effective in this task is that it combines weak learners and creates a strong ensemble model that can predict if traffic belongs to a normal or malicious one with high accuracy. This paper indicates that the GBDT-IDS model is able to improve network security significantly and has better features in terms of both real-time detection accuracy and low false positive rates. In future work, we will integrate this model into live SDN space to observe its application and scalability. This research serves as an initial base on which one can make further strides forward to enhance security in SDN using ML techniques and have more secure, resilient networks.

翻译：软件定义网络（SDN）是一种新型网络架构，它使网络控制层可直接编程，并将底层基础设施从应用程序和网络服务中抽象出来（控制平面）。在安全性方面，这种集中化架构容易遭受其他网络架构中不常见的各类网络威胁。本研究提出了一种新颖的机器学习方法来捕获网络感染。我们将分类器应用于UNSW-NB15入侵检测基准数据集，并基于该数据训练模型。研究采用随机森林和决策树作为基础分类器，并与梯度提升和AdaBoost进行对比评估。其中性能最佳的模型是梯度提升，其准确率、召回率和F1分数分别达到99.87%、100%和99.85%，这表明其在SDN网络入侵检测中具有高度可靠性。性能第二的分类器是随机森林，准确率为99.38%，随后是AdaBoost和决策树。研究表明，梯度提升在此任务中表现卓越的原因在于其通过集成弱学习器构建了强大的组合模型，能够以高精度预测流量属于正常还是恶意类别。本文表明GBDT-IDS模型能显著提升网络安全性，在实时检测精度和低误报率方面均具有优越特性。未来工作中，我们将把该模型部署到实际SDN环境中，以验证其应用效果和可扩展性。本研究为利用机器学习技术增强SDN安全性奠定了初步基础，有助于构建更安全、更具韧性的网络体系。