New answers tagged


I think the problem is that this type of attack will only work for the model that was used to produce the perturbations. These perturbations are computed by backpropagating an error for an image of, say, a panda, but with the true label "airplane". In other words, perturbations are nothing more than gradients indicating in which direction each ...


Because the examples are fit to a particular ML model and if you train using different parameters they probably won't be valid.

Top 50 recent answers are included