I am 14 years and am a NN/ML CS enthusiast (perhaps some of you have seen my NN troubles on SO). I have this question: is it computationally plausible to use NN/ML to do any of the following tasks? (I have a vague idea of how to program these)
"Real" cryptanalysis. Cyclic neural networks for extended computation, but break the hash all the way through.
Estimating the entropy of the plaintext from the ciphertext.
Any other cryptanalysis tricks or procedures.