We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
A novel deep-learning based approach to DNS over HTTPS network traffic detection.
- Authors
Fesl, Jan; Konopa, Michal; Jelínek, Jiří
- 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.
- Subjects
COMPUTER network traffic; DEEP learning; TRAFFIC monitoring; HTTP (Computer network protocol); INTERNET domain naming system; SECURE Sockets Layer (Computer network protocol)
- Publication
International Journal of Electrical & Computer Engineering (2088-8708), 2023, Vol 13, Issue 6, p6691
- ISSN
2088-8708
- Publication type
Article
- DOI
10.11591/ijece.v13i6.pp6691-6700