Omni SCADA Intrusion Detection Using Deep Learning Algorithms
Jun Gao, Luyun Gan, Fabiola Buschendorf, Liao Zhang, Hua Liu, Peixue Li, Xiaodai Dong, Tao Lu
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
We investigate deep learning based omni intrusion detection system (IDS) for supervisory control and data acquisition (SCADA) networks that are capable of detecting both temporally uncorrelated and correlated attacks. Regarding the IDSs developed in this paper, a feedforward neural network (FNN) can detect temporally uncorrelated attacks at an F_1 of 99.9670.005\% but correlated attacks as low as 582\%. In contrast, long-short term memory (LSTM) detects correlated attacks at 99.560.01\% while uncorrelated attacks at 99.30.1\%. Combining LSTM and FNN through an ensemble approach further improves the IDS performance with F_1 of 99.680.04\% regardless the temporal correlations among the data packets.