Cracking Random Number Generators using Machine Learning – Part 2: Mersenne Twister

After a few hours and manual tweaking of the model architecture, we have trained a model that has achieved 100% bitwise accuracy for both the training and testing sets. To be more confident about what we have achieved, we have generated a new sample of 1000,000 states generated using a different seed than the one used to generate the previous data. We got the same result of 100% bitwise accuracy when we tested with the newly generated data. This means that the model has learned the exact formula that relates each state to the three previous states. Hence if we got access to the three internal states at those specific locations, we could predict the next state.