Re:Images that fool computer vision raise security concerns
by compbio on Monday March 23, 2015 @02:18PM
(#9252486)
Very interesting. Thank you for correcting me.
a relatively large fraction of examples will be misclassified by networks trained from scratch with different hyper-parameters (number of layers, regularization or initial weights). The above observations suggest that adversarial examples are somewhat universal...
a relatively large fraction of examples will be misclassified by networks trained from scratch with different hyper-parameters (number of layers, regularization or initial weights). The above observations suggest that adversarial examples are somewhat universal...