News for hackers. Stuff that matters.
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!

There are no comments on this comment yet.