LTU Attacker for Membership Inference

1 code implementation • 4 Feb 2022 • Joseph Pedersen, Rafael Muñoz-Gómez, Jiangnan Huang, Haozhe Sun, Wei-Wei Tu, Isabelle Guyon

In both cases classification accuracy or error rate are used as the metric: Utility is evaluated with the classification accuracy of the Defender model; Privacy is evaluated with the membership prediction error of a so-called "Leave-Two-Unlabeled" LTU Attacker, having access to all of the Defender and Reserved data, except for the membership label of one sample from each.

Inference Attack Membership Inference Attack