avaxzat

The one-pixel attack works for pretty much any machine learning model, not just one single neural network.

>I'm curious if the attack adds doubt, in that the prediction algorithm is _close_ to truth but gets confused (likelihood of horse slightly less than dog), versus incorrect certitude (the horse is definitely a dog).

While I can't speak for this attack in particular, there exist algorithms that can fool a neural network into generating high-confidence incorrect predictions for images that are visually indistinguishable from ones on which the network performs just fine. That's the biggest issue with these adversarial images.

>I'm curious whether training the network by adding noise and other mutations to the set would make the network more resilient to this attacks. In other words, it's the training set or the network architecture that's vulnerable here?

This is called adversarial training and is currently the most popular technique for protecting neural networks against this type of attack. That being said, it doesn't work as well as one would hope: the adversarially trained models are usually still vulnerable to other attacks.

Mozilla Firefox ships as the default browser with almost every Linux distro. Why is this not a problem? Is that hypocrisy really lost on everyone but me?