Papers
arxiv:2409.10643

CaBaGe: Data-Free Model Extraction using ClAss BAlanced Generator Ensemble

Published on Sep 16, 2024
Authors:
,
,
,

Abstract

CaBaGe is a data-free model extraction method that improves accuracy and reduces query count by using experience replay, an ensemble of generators, and selective filtering, even when the number of classes is unknown.

AI-generated summary

Machine Learning as a Service (MLaaS) is often provided as a pay-per-query, black-box system to clients. Such a black-box approach not only hinders open replication, validation, and interpretation of model results, but also makes it harder for white-hat researchers to identify vulnerabilities in the MLaaS systems. Model extraction is a promising technique to address these challenges by reverse-engineering black-box models. Since training data is typically unavailable for MLaaS models, this paper focuses on the realistic version of it: data-free model extraction. We propose a data-free model extraction approach, CaBaGe, to achieve higher model extraction accuracy with a small number of queries. Our innovations include (1) a novel experience replay for focusing on difficult training samples; (2) an ensemble of generators for steadily producing diverse synthetic data; and (3) a selective filtering process for querying the victim model with harder, more balanced samples. In addition, we create a more realistic setting, for the first time, where the attacker has no knowledge of the number of classes in the victim training data, and create a solution to learn the number of classes on the fly. Our evaluation shows that CaBaGe outperforms existing techniques on seven datasets -- MNIST, FMNIST, SVHN, CIFAR-10, CIFAR-100, ImageNet-subset, and Tiny ImageNet -- with an accuracy improvement of the extracted models by up to 43.13%. Furthermore, the number of queries required to extract a clone model matching the final accuracy of prior work is reduced by up to 75.7%.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2409.10643 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2409.10643 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2409.10643 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.