Re:Image GPT
by aquajet on Wednesday June 17, 2020 @08:41PM
(#23558565)
Could you elaborate a bit more? What were the differences between transformer adversarial examples and cnn adversarial examples?
[ Parent
| on HN ]
Re:Image GPT
by markchen90 on Wednesday June 17, 2020 @10:11PM
(#23559097)
I didn't notice any obvious visual differences, but I'm also not an expert on adversarial examples. The transformer models were similarly susceptible to attacks, but while adversarial examples transferred well within a model class (~40%), they did not across model classes (~5%). These are rough numbers from memory, don't hold me accountable!