CNN-Enhanced Network Security: A Sustainable Approach to Anomaly Detection

Cybersecurity remains a critical challenge in today’s digital landscape, impacting various industries while aligning with key Sustainable Development Goals (SDGs). Notably, it connects with SDG 9, which focuses on fostering innovation and building resilient infrastructure, and SDG 16, which emphasizes promoting peace, justice, and strong institutions. The increasing sophistication and frequency of cyber threats call for novel approaches, as traditional methods of detecting anomalous behavior are often inadequate in addressing these evolving risks. This research introduces an innovative approach to detecting unusual activity in network traffic by leveraging Convolutional Neural Networks (CNNs). The model is trained and evaluated on a comprehensive set of normal and abnormal network events from the CICIDS2017 dataset. The CNN-based approach achieved a notable accuracy of 93.64%, significantly outperforming conventional detection methods. This advancement not only enhances cybersecurity efforts but also contributes to the promotion of SDG 9 by fostering innovative solutions and reinforcing infrastructure. Additionally, the model aids in identifying and mitigating cyber threats, supporting the objectives of SDG 16 by strengthening institutions and ensuring more secure systems. The results, including performance curves, accuracy, recall, F1 score, and confusion matrices, provide a thorough assessment of the model’s effectiveness. These findings underscore the critical role of advanced machine learning techniques, particularly deep learning, in bolstering cybersecurity systems. The capacity of CNNs to detect network anomalies with high accuracy demonstrates their potential to transform cybersecurity practices. This work highlights the need for continued exploration and application of deep learning methods in the face of escalating cybersecurity challenges, which in turn supports the achievement of key sustainable development goals and contributes to the stability and security of digital infrastructures.