Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Fentham, Daniel"'
When deploying classifiers in the real world, users expect them to respond to inputs appropriately. However, traditional classifiers are not equipped to handle inputs which lie far from the distribution they were trained on. Malicious actors can expl
Externí odkaz:
http://arxiv.org/abs/2309.06359
