Deep neural networks (DNNs) have become the essential components for various commercialized machine learning services, such as Machine Learning as a Service (MLaaS). Recent studies show that machine learning services face severe privacy threats - well-trained DNNs owned by MLaaS providers can be stolen through public APIs, namely model stealing attacks. However, most existing works undervalued the impact of such attacks, where a successful attack has to acquire confidential training data or auxiliary data regarding the victim DNN. In this paper, we propose ES Attack, a novel model stealing attack without any data hurdles. By using heuristically generated synthetic data, ES Attack iteratively trains a substitute model and eventually achieves a functionally equivalent copy of the victim DNN. The experimental results reveal the severity of ES Attack: i) ES Attack successfully steals the victim model without data hurdles, and ES Attack even outperforms most existing model stealing attacks using auxiliary data in terms of model accuracy; ii) most countermeasures are ineffective in defending ES Attack; iii) ES Attack facilitates further attacks relying on the stolen model.
@article{arxiv.2009.09560,
title = {ES Attack: Model Stealing against Deep Neural Networks without Data Hurdles},
author = {Xiaoyong Yuan and Leah Ding and Lan Zhang and Xiaolin Li and Dapeng Wu},
journal= {arXiv preprint arXiv:2009.09560},
year = {2022}
}
Comments
accepted to IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI)