Re:How Adversarial Attacks Work
by yters on Friday November 03, 2017 @06:36PM
(#15622649)
You think these are equivalent to changing a single pixel and causing a complete misperception of the object which is believed with almost 100% certainty?
[ Parent
| on HN ]
Re:How Adversarial Attacks Work
by red75prime on Sunday November 05, 2017 @05:38AM
(#15628906)
Single pixel attack is an artifact of the network architecture. It is not inherent vulnerability of every ML technique.