Abstract
Abstract With the development of the times, the demand for privacy and security by people, enterprises and government units has become stronger and stronger, driven by this, encrypted traffic has shown a blowout growth, and the security of traffic has become an issue that cannot be ignored. To solve the traffic classification problem, this paper proposes a new traffic classification algorithm based on convolutional neural network and multi-head attention mechanism. In addition, this paper uses a feature engineering method based on representation learning and proposes a discard threshold to improve the quality of data sets obtained by feature engineering. The experimental results show that the algorithm model and the optimized feature engineering method proposed in this paper have good performance on the traffic classification task.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
