Membership Inference Attacks From First Principles

A membership inference attack allows an adversary to query a trained machine learning model to predict whether or not a particular example was contained in the model's training dataset. These attacks are currently evaluated using average-case "accuracy" metrics that fail to characteri...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings - IEEE Symposium on Security and Privacy pp. 1897 - 1914
Main Authors: Carlini, Nicholas, Chien, Steve, Nasr, Milad, Song, Shuang, Terzis, Andreas, Tramer, Florian
Format: Conference Proceeding
Language:English
Published: IEEE 01.05.2022
Subjects:
Computational modeling
Differential privacy
Machine learning
Measurement
Privacy
Training
Training data
ISSN:2375-1207
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A membership inference attack allows an adversary to query a trained machine learning model to predict whether or not a particular example was contained in the model's training dataset. These attacks are currently evaluated using average-case "accuracy" metrics that fail to characterize whether the attack can confidently identify any members of the training set. We argue that attacks should instead be evaluated by computing their true-positive rate at low (e.g., ≤ 0.1%) false-positive rates, and find most prior attacks perform poorly when evaluated in this way. To address this we develop a Likelihood Ratio Attack (LiRA) that carefully combines multiple ideas from the literature. Our attack is 10\times more powerful at low false-positive rates, and also strictly dominates prior attacks on existing metrics.
ISSN:2375-1207
DOI:10.1109/SP46214.2022.9833649