Statistical Metamorphic Testing of Neural Network Based Intrusion Detection Systems 2021 https://www.cs.montana.edu/izurieta/pubs/IEEE_CSR_2021.pdf This paper proposes a statistical metamorphic testing technique to test neural network-based Network Intrusion Detection Systems (N-IDSs) in nondeterministic environments. The approach addresses the stochastic nature of these applications where multiple runs with the same input can produce slightly different results. The method demonstrated strong defect detection capabilities, effectively identifying implementation bugs in two neural network-based N-IDSs and a cancer prediction system