Deep learning has been applied in the field of network intrusion detection and has yielded good results. In malicious network traffic classification tasks, many studies have achieved good performance with respect to the accuracy and recall rate of classification through self-designed models. In deep learning, the design of the model architecture greatly influences the results. However, the design of the network model architecture usually requires substantial professional knowledge. At present, the focus of research in the field of traffic monitoring is often directed elsewhere. Therefore, in the classification task of the network intrusion detection field, there is much room for improvement in the design and optimization of the model architecture. A neural architecture search (NAS) can automatically search the architecture of the model under the premise of a given optimization goal. For this reason, we propose a model that can perform NAS in the field of network traffic classification and search for the optimal architecture suitable for traffic detection based on the network traffic dataset. Each layer of our depth model is constructed according to the principle of maximum coding rate attenuation, which has strong consistency and symmetry in structure. Compared with some manually designed network architectures, classification indicators, such as Top-1 accuracy and F1 score, are also greatly improved while ensuring the lightweight nature of the model. In addition, we introduce a surrogate model in the search task. Compared to using the traditional NAS model to search the network traffic classification model, our NAS model greatly improves the search efficiency under the premise of ensuring that the results are not substantially different. We also manually adjust some operations in the search space of the architecture search to find a set of model operations that are more suitable for traffic classification. Finally, we apply the searched model to other traffic datasets to verify the universality of the model. Compared with several common network models in the traffic field, the searched model (NAS-Net) performs better, and the classification effect is more accurate.
Cascading failure phenomena widely exist in real-life circumstances, such as the blackouts in power networks and the collapse in computer networks. In this paper, we construct a cascading failure model on the multilayer network, taking into account the number of invalid neighbors of nodes, the failure frequency of nodes, the effect between layers, and the percolation process. To minimize network losses caused by the cascading process, we propose a recovery strategy, i.e. repairing some certain clusters formed by ineffective nodes and links. The recovery strategy is discussed in detail, like whether to add links to the network, how many links are needed at least to add, how many layers are demanded to restore, and how to choose the values of [Formula: see text] and restorable threshold [Formula: see text] to improve the network performance. Besides, we theoretically analyze the cascading failure model with recovery strategy by virtue of mean-field approximation and generating function techniques. The theoretical solutions are found to be consistent with experimental results simulated on the ER as well as BA networks. In addition, we also investigate the affecting factors of network robustness. The effects of failure threshold [Formula: see text], base number [Formula: see text], and threshold [Formula: see text] between layers on network behaviors depend on the values of average degree [Formula: see text] and recovery proportion [Formula: see text]. These results may provide particular reference significance for maintaining system security, adjusting the network performance, and enhancing network robustness.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.