41–50 of 84 posts
Earlier quoted context omitted.
That's only because the attack is designed to target that particular network. Just wait until we understand real brains better and can generate tailored attacks...
Isn't that basically what an optical illusion is?
Hacks human brain rather efficiently.
I’ve mentioned this before but a median filter would nuke the single outlying pixel without too much of an effect on the input image. Is there an attack that can get past such a basic preprocessing step?
Earlier quoted context omitted.
The fact that a human isn't fooled by the attack (we can still recognize the 32x32 images for what they are), points to an interesting gap in the abilities of conventional convolutional neural nets.
That's only because the attack is designed to target that particular network. Just wait until we understand real brains better and can generate tailored attacks...
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?
I’ve mentioned this before but a median filter would nuke the single outlying pixel without too much of an effect on the input image. Is there an attack that can get past such a basic preprocessing step?
It would be an interesting experiment.
Earlier quoted context omitted.
Jumping on top comment (which I completely agree with) to ask: Why wouldn't a K-fold cross validation enable catching this? 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). One could then attach a weighting, perhaps based on max RGB/CYMK vector norm betw…
I don't believe that many people are using K-fold cross validation at all with deep learning, as the computational overhead is massive.
Earlier quoted context omitted.
I don't believe that many people are using K-fold cross validation at all with deep learning, as the computational overhead is massive.
I must be misspeaking then. I'm not suggesting it run during training, but run the classification algorithm X number of times over an input image with chunks areas removed/suppressed from the data.
Earlier quoted context omitted.
I don't believe that many people are using K-fold cross validation at all with deep learning, as the computational overhead is massive.
I must be misspeaking then. I'm not suggesting it run during training, but run the classification algorithm X number of times over an input image with chunks areas removed/suppressed from the data.
It does make the model more robust, but doesn't seem to help much with finding adversarial examples in the model.
Generating adversarial examples and training on that might be a better approach to solving this.
This is really interesting, but points out a key importance in training neural nets, which is to design your dataset and training to maximize generalization. For example, in the case of training a neural network for something that is highly safety critical, like an autonomous vehicle, it's important for vehicle and pedestrian detection to be as generalized as possible. In order to achieve high confidence in all sorts…
Walk around in the city with a giant yellow square costume and observe the mayhem...
Don’t put breaking expectations past humans. We are adversarial by nature.
I’ve mentioned this before but a median filter would nuke the single outlying pixel without too much of an effect on the input image. Is there an attack that can get past such a basic preprocessing step?