Re:Adversarial image attacks are no joke
by meiji163 on Monday November 29, 2021 @10:43AM
(#29381096)
Language models have the same defect - they are quite brittle and susceptible to black-box adversarial attacks ( eg arxiv.org/abs/1907.11932 )
[ Parent
| on HN ]
There are no comments on this comment yet.