Purifier: Defending Data Inference Attacks via Transforming Confidence Scores. (arXiv:2212.00612v1 [cs.LG])

Neural networks are susceptible to data inference attacks such as the
membership inference attack, the adversarial model inversion attack and the
attribute inference attack, where the attacker could infer useful information
such as the membership, the reconstruction or the sensitive attributes of a
data sample from the confidence scores predicted by the target classifier. In
this paper, we propose a method, namely PURIFIER, to defend against membership
inference attacks. It transforms the confidence score vectors predicted by the
target classifier …

attacks data