1
$\begingroup$

I am seeking adversarial examples for classifiers (e.g. random forest, logistic regression, multilayer perceptron) that I've already trained (through scikit-learn). But I can't seem to find any existing libraries for this purpose. This could be a fun project for me to start, but before beginning to explore my naïveté, is there any literature/code on this topic that I should be considering?

$\endgroup$
1
$\begingroup$

Try foolbox

Foolbox is a Python toolbox to create adversarial examples that fool neural networks. It requires Python, NumPy and SciPy.

Also, join the google group of cleverhans, it's really good. Plus Ian Goodfellow is there along with Nicolas Papernot.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.