Robustness May Be at Odds with Accuracy · HackerPapers discussions

Robustness May Be at Odds with Accuracy — mentioned by red75prime

Tue, 03 Jul 2018 18:19:32 GMT

In the light of [0], it seems that standard (not adversarially trained) NNs learn each and every feature which happens to correlate with a class label in a training set (including noise). So moving along adversarial gradient looks like noise. Take my interpretation with a (huge) grain of salt. [0] https://arxiv.org/abs/1805.12152

Paper and discussion history. A mention is not an endorsement.

Robustness May Be at Odds with Accuracy — mentioned by logane

Mon, 02 Jul 2018 15:35:24 GMT

We took a look at adversarial examples for linear classifiers (and in general, we looked at properties that adversarial training induces) here: https://arxiv.org/abs/1805.12152 For $\ell_\infty$ adversarial examples on linear classifiers we found that adversarial training forces a tradeoff between the $\ell_1$ norm of the weights (which is directly associated with adversarial accuracy) and accuracy. It looks like this article works through something vaguely similar for $\ell_2$ adversarial examples. It would be interesting to compare the author's approach with explicit adversarial training.

Paper and discussion history. A mention is not an endorsement.

Robustness May Be at Odds with Accuracy — mentioned by red75prime

Sun, 03 Jun 2018 06:34:01 GMT

Adversarially robust classifiers have interpretable gradients and feature representations [0]. The problem seems to be that the standard networks capture all the statistics there is, including surface statistical regularities and noise. It can be mitigated, though. [0]: https://arxiv.org/abs/1805.12152

Paper and discussion history. A mention is not an endorsement.