Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting

arXiv:2306.05093v2 Announce Type: replace-cross
Abstract: Machine learning models have been shown to leak sensitive information about their training datasets. Models are increasingly deployed on devices, raising concerns that white-box access to the model parameters increases the attack surface compared to black-box access which only provides query access. Directly extending the shadow modelling technique from the black-box to the white-box setting has been shown, in general, not to perform better than black-box only attacks. A potential reason is misalignment, a known …

abstract arxiv box concerns cs.cr cs.lg datasets devices information leak machine machine learning machine learning models parameters privacy query surface training training datasets type