Year: 2023
Type: article
Abstract: 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.
Authors: Jan Fesl, Michal Konopa, Jiří Jelínek
Institution: University of South Bohemia in České Budějovice
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4386999805
