Table 3 Description of datasets used for anomaly detection.
From: Anomaly detection in encrypted network traffic using self-supervised learning
Dataset | Total flows | Traffic type | Key features |
|---|---|---|---|
CIC-Darknet2020 | 10,000,000 + | Encrypted and non-encrypted | Packet size, Inter-arrival times, Flow duration, Protocol |
ISCX VPN-nonVPN | 250,000 + | VPN and non-VPN traffic | Encryption type, Flow duration, Traffic direction |
UNSW-NB15 | 2,540,044 | Mixed (normal and malicious) | Connection states, Protocol types, Statistical features |
