Re:Image GPT
by markchen90 on Wednesday June 17, 2020 @07:03PM
(#23557869)
Author here. I ran some early experiments a while ago, and it looked like adversarial examples for convnet classifiers didn't transfer to transformer classifiers and vice versa. Definitely worth looking more into!
[ Parent
| on HN ]
Could you elaborate a bit more? What were the differences between transformer adversarial examples and cnn adversarial examples?
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!