Affiliation:
1. Education Information Technology Center, China West Normal University, Nanchong 637001, China
2. School of Computer Science, China West Normal University, Nanchong 637001, China
3. School of Electronic and Information Engineering, China West Normal University, Nanchong 637001, China
Abstract
With the continuous expansion of the darknet and the increase in various criminal activities in the darknet, darknet traffic identification has become increasingly essential. However, existing darknet traffic identification methods rely on all traffic characteristics, which require a long computing time and a large amount of system resources, resulting in low identification efficiency. To this end, this paper proposes an autoencoder-based darknet traffic identification method (AE-DTI). First, AE-DTI maps the feature values to pixels of a two-dimensional grayscale image after deduplication and denoising of the darknet traffic dataset. Then, AE-DTI designs a new feature selection algorithm (AE-FS) to downscale the grayscale graph, and AE-FS trains a feature scoring network, which globally scores all the features based on the reconstruction error to select the features with scores greater than or equal to a set threshold value. Finally, AE-DTI uses a one-dimensional convolutional neural network with a dropout layer to identify darknet traffic on the basis of alleviating overfitting. Experimental results on the ISCXTor2016 dataset show that, compared with other dimensionality reduction methods (PCA, LLE, ISOMAP, and autoencoder), the classification model trained with the data obtained from AE-FS has a significant improvement in classification accuracy and classification efficiency. Moreover, AE-DTI also shows significant improvement in recognition accuracy compared with other models. Experimental results on the CSE-CIC-IDS2018 dataset and CIC-Darknet2020 dataset show that AE-DTI has strong generalization.
Funder
Sichuan Science and Technology Program
China Scholarship Council Program
Innovation Team Funds of China West Normal University
Nanchong Federation of Social Science Associations Program
China West Normal University 2022 University-level College Student Innovation and Entrepreneurship Training Program Project
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference30 articles.
1. The Anonymity of the Dark Web: A Survey;Saleem;IEEE Access,2022
2. A Dive into the Dark Web: Hierarchical Traffic Classification of Anonymity Tools;Montieri;IEEE Trans. Netw. Sci. Eng.,2019
3. A Survey on Internet Traffic Identification;Callado;IEEE Commun. Surv. Tutor.,2009
4. Network traffic classification for data fusion: A survey;Zhao;Inf. Fusion,2021
5. Li, W., and Moore, A.W. (2007, January 24–26). A Machine Learning Approach for Efficient Traffic Classification. Proceedings of the 2007 15th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, Istanbul, Turkey.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献