Jiří Jelínek
Research Subjects
Research Interests
Jiří Jelínek has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Jan Fesl
Department of Computer Systems, Faculty of Information Technology, Czech Technical University in Prague, Prague, Czech Republic
1 shared publication - Michal Konopa
Department of Data Science and Computer Systems Faculty of Agriculture and Technology University of South Bohemia Czech Republic
1 shared publication
Latest Publications
- Open Access
- 1 December 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (6) , 6691-6700
A novel deep-learning based approach to DNS over HTTPS network traffic detection
Domain name system (DNS) over hypertext transfer protocol secure (HTTPS) (DoH) is currently a new standard for secure communication between DNS servers and end-users. Secure sockets layer (SSL)/transport layer security (TLS) encryption should guarantee the user a high level of privacy regarding the impossibility of data content decryption and protocol identification. Our team created a DoH data set from captured real network traffic and proposed novel deep-learning-based detection models allowing encrypted DoH traffic identification. Our detection models were trained on the network traffic from the Czech top-level domain maintainer, Czech network interchange center (CZ.NIC), and successfully applied to the identification of the DoH traffic from Cloudflare. The reached detection model accuracy was near 95%, and it is clear that the encryption does not prohibit the DoH protocol identification.
- 1 December 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (6) , 6691-6700
Open AccessA novel deep-learning based approach to DNS over HTTPS network traffic detection
Domain name system (DNS) over hypertext transfer protocol secure (HTTPS) (DoH) is currently a new standard for secure communication between DNS servers and end-users. Secure sockets layer (SSL)/transport layer security (TLS) encryption should guarantee the user a high level of privacy regarding the impossibility of data content decryption and protocol identification. Our team created a DoH data set from captured real network traffic and proposed novel deep-learning-based detection models allowing encrypted DoH traffic identification. Our detection models were trained on the network traffic from the Czech top-level domain maintainer, Czech network interchange center (CZ.NIC), and successfully applied to the identification of the DoH traffic from Cloudflare. The reached detection model accuracy was near 95%, and it is clear that the encryption does not prohibit the DoH protocol identification.