ترجمه مقاله نقش ضروری ارتباطات 6G با چشم انداز صنعت 4.0
- مبلغ: ۸۶,۰۰۰ تومان
ترجمه مقاله پایداری توسعه شهری، تعدیل ساختار صنعتی و کارایی کاربری زمین
- مبلغ: ۹۱,۰۰۰ تومان
Abstract
Software-Defined Networks (SDN) initiates a novel networking model. SDN proposes the separation of forward and control planes by introducing a new independent plane called network controller. The architecture enhances the network resilient, decompose management complexity, and support more straightforward network policies enforcement. However, the model suffers from severe security threats. Specifically, a centralized network controller is a precious target for two reasons. First, the controller is located at a central point between the application and data planes. Second, a controller is software which prone to vulnerabilities, e.g., buffer and stack overflow. Hence, providing security measures is a crucial procedure towards the fully unleash of the new model capabilities. Intrusion detection is an option to enhance the networking security. Several approaches were proposed, for instance, signature-based, and anomaly detection. Anomaly detection is a broad approach deployed by various methods, e.g., machine learning. For many decades intrusion detection solution suffers performance and accuracy deficiencies. This paper revisits network anomalies detection as recent advances in machine learning particularly deep learning proofed success in many areas like computer vision and speech recognition. The study proposes an intrusion detection framework based on unsupervised deep learning algorithms.
CONCLUSION
Deep learning algorithms achieved a breakthrough in neural networks. With a strong record of successful applications, deep learning is a promising approach for network anomalies detection. The paper showed the potential of unsupervised deep learning to enhance the security of SDN. We applied deep autoencoders to calculate a reconstruction error for network traffic records. Then we apply a K-means as clustering algorithm on REs. Our approach showed robust prediction with reasonable training data. However, further research should investigate dimensionality in traffic records, where the number of dimensions is relatively small.