Two-dimensional layered transition-metal dichalcogenides (2D-TMDs) have garnered significant attention due to their layer number-dependent electronic properties, making them promising candidates for atomically thin electronics and optoelectronics. However, current research has primarily focused on exfoliated TMD materials, which have limitations in size, layer number control, and yield. Therefore, a crucial challenge remains in producing large single TMD crystals with precise control over the layer number. A comprehensive understanding and precise control of the growth conditions are imperative to address this challenge. This study systematically investigated key growth conditions, including temperature, precursor flow, growth duration, material quantity, gas flow, and slide position. By optimizing these parameters, we successfully synthesized TMD materials with an impressive size of 850 µm. Notably, we achieved the preparation of monolayer WS2 single crystals on a large scale within a remarkably short duration of 10 min, exhibiting a lateral growth rate of up to 1.4 μm/s, which is comparable to the best-exfoliated monolayers. The findings from our study provide a robust pathway for the rapid growth of high-quality TMD single crystals, facilitating further advancements in this field.
With the widespread adoption of Software-Defined Networking (SDN) infrastructures that give a flexible architecture and make this network more reliable, network security has become a critical concern. Expressly, the Control Plane assumes a crucial role within this architecture and is often regarded as the brain of SDN. However, due to this centralization, the Control Plane is often the target of Distributed Denial of Service (DDoS) attack attacks, which are increasingly sophisticated. In the same context, most DDoS solutions are concentrated in the Control Plane, which has many other tasks and responsibilities. This study investigates the potential advantages and obstacles associated with relocating DDoS attack detection to the data plane, aligning with the growing prevalence of Programmable Data Planes utilizing the Programming Protocol-Independent Packet Processors (P4) language. To optimize resource utilization in combatting DDoS attacks.
This paper introduces a novel approach for detecting Distributed Denial of Service (DDoS) attacks in Software-Defined Networking (SDN) environments, addressing the critical need for accurate and efficient threat detection in modern network infrastructures. The proposed method integrates dimensionality reduction, feature engineering, and machine learning (ML) into a cohesive pipeline. Specifically, it combines Principal Component Analysis (PCA) and t-Distributed Stochastic Neighbor Embedding (t-SNE) for dimensionality reduction, followed by K-Means clustering to enhance feature representation. Cluster assignments (Benign/Attack) derived from the t-SNE-reduced data are incorporated as a new feature, enabling classifiers to detect latent attack patterns more effectively than traditional methods. When evaluated on a real-world SDN dataset, the method significantly outperformed existing approaches, achieving over 99.9% accuracy with Random Forest (RF) and XGBoost classifiers. Notably, XGBoost processed data in just 0.2 seconds, demonstrating exceptional suitability for real-time applications. Furthermore, the ensemble model, combining RF and XGBoost, achieved the highest overall accuracy of 99.93%, an AUC of 1.00, and an execution time of 1.61 seconds. These results underscore the proposed approach's substantial improvements in accuracy and computational efficiency making it a robust solution for addressing critical network security challenges in SDN environments.