The predetection evolution of stress corrosion cracking has been examined as a necessary preliminary to effective detection of such cracks. Anodic dissolution (AD) and hydrogen embrittlement (HE) have been considered to calculate the stress corrosion crack (SCC) growth in AA7050-T6 for a surface-breaking crack with blunt tip in an aqueous environment. Since these processes are not completely deterministic, several advanced statistical methods have been used to introduce probabilistic considerations. Based on the data from designed computer experiments, the computer code developed by the authors (Lee et al., 2015, “A Comprehensive Analysis of the Growth Rate of Stress Corrosion Cracks,” Proc. R. Soc. A, 471(2178), p. 20140703) to conduct deterministic stress corrosion crack growth analysis has been represented by metamodels using Gaussian process regression. Through sensitivity analysis, important variables which need to be calibrated have been identified. The dynamic Bayesian network (DBN) model and Monte Carlo simulation (MCS) have been utilized to quantify uncertainties. Statistical parameters of input variables have been obtained by a machine learning technique. The calibrated model has been validated using Bayesian hypothesis testing. Since the DBN model yields a probability of detection (POD) comparable to the probability based on binary validation data, the probabilistic model with calibrated parameters is expected to well represent the growth of a stress corrosion crack. The results also show that the reliability largely depends on the accuracy of flaw detection methods and on the critical crack length.