Adversarial ML / privacy
Privacy
Models memorise, and memorisation is detectable. The question these entries formalise is how confidently an adversary can decide whether a particular record was in the training set.
1 entry.
Adversarial ML / privacy
Models memorise, and memorisation is detectable. The question these entries formalise is how confidently an adversary can decide whether a particular record was in the training set.
1 entry.