On Detecting Adversarial Perturbations — mentioned by derEitel

Sat, 20 May 2017 16:49:33 GMT

Here is a paper from Bosch in that direction, it uses a second network to classify examples as adversarials: https://arxiv.org/abs/1702.04267 Using a fail safe network is hard because adversarial examples usually have a high accuracy at a false class. So using an accuracy threshold in the main network wouldn't work. Using a network as described in the paper and then a different kind of classifier might be worth trying. But it has also been shown that adversarial examples can transfer to different kind of models (don't know if random forests have been tried as well).

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

On Detecting Adversarial Perturbations · HackerPapers discussions

On Detecting Adversarial Perturbations — mentioned by derEitel