[haraldurt]

Not necessarily. Adversarial examples have been shown to, for instance, be transferable across different networks with different hyperparameters (e.g., number of layers) trained on disjoint subsets of a training set [0, section 4.2]. There are more references from the paper linked by the OP.

[0] https://arxiv.org/abs/1312.6199

[naveen99]

Thanks. I wonder if adversarial training helps prevent overfitting too. Could you use adversarial training to beat alphago ?

[yorwba]

You could not, because AlphaGo is not a classifier (so it isn't well-defined what an adversarial example is) and the input space is discrete (Go board state) and you can't do ε-small perturbations (two different states differ by at least one stone).