Research Article

An Intrusion Detection System for the Internet of Things Based on the Ensemble of Unsupervised Techniques

Table 9

Performance (%) of the four intrusion detection methods on the IoT dataset.

Attack typeMetricUTEN-IDSAE-IDSKitNETAE

MQTT brute forceRecall (%)99.45100100100
F1 (%)99.4899.0785.1467.24
AA (%)99.6299.5992.3378.57

Sparta SSH brute forceRecall (%)10099.31100100
F1 (%)99.7399.6584.7966.61
AA (%)99.8999.6592.3478.60