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...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings - IEEE Symposium on Security and Privacy s. 1897 - 1914
Hlavní autori: Carlini, Nicholas, Chien, Steve, Nasr, Milad, Song, Shuang, Terzis, Andreas, Tramer, Florian
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.05.2022
Predmet:
Computational modeling
Differential privacy
Machine learning
Measurement
Privacy
Training
Training data
ISSN:2375-1207
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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