One pixel attack for deceiving deep neural networks

Re:One pixel attack for deceiving deep neural networks by Donald on Sunday October 29, 2017 @01:17AM (#15578060)

See https://arxiv.org/abs/1610.08401 for model agnostic examples of adversarial attacks.

[ Parent | on HN ]

Re:One pixel attack for deceiving deep neural networks by justifier on Sunday October 29, 2017 @10:26PM (#15582734)

This is a great paper.. the perturbation map is very reminiscent of psychedelic imagery

Psychedelics come up a lot with nn created images, but this is interesting that under the influence of a perturbation suddenly the classifier starts presenting illogical assumptions

Also similar to how people recollect their own classifiers unfolding or showing bias when considered under the influence of psychedelics

Perhaps there is some deeper analogue with a substance influenced brain's neuronal activity

[ Parent | on HN ]

Re:One pixel attack for deceiving deep neural networks by jszymborski on Sunday October 29, 2017 @01:41PM (#15580344)

This is great stuff! I've noticed that the inter-model universality is OK (a little over 50% for one of the universal pertubations), but that's still pretty good!

[ Parent | on HN ]

Re:One pixel attack for deceiving deep neural networks by IshKebab on Sunday October 29, 2017 @05:23AM (#15578638)

This is much more interesting, thanks!

[ Parent | on HN ]