An extraction attack on image recognition model using VAE-kdtree model

Tianqi Wen; Haibo Hu; Huadi Zheng

doi:10.1117/12.2590844

13 March 2021 An extraction attack on image recognition model using VAE-kdtree model

Tianqi Wen, Haibo Hu, Huadi Zheng

Proceedings Volume 11766, International Workshop on Advanced Imaging Technology (IWAIT) 2021; 117660N (2021) https://doi.org/10.1117/12.2590844
Event: International Workshop on Advanced Imaging Technology 2021 (IWAIT 2021), 2021, Online Only

Abstract

This paper proposes a black box extraction attack model on pre-trained image classifiers to rebuild a functionally equivalent model with high similarity. Common model extraction attacks use a large number of training samples to feed the target classifier which is time-consuming with redundancy. The attack results have a high dependency on the selected training samples and the target model. The extracted model may only get part of crucial features because of inappropriate sample selection. To eliminate these uncertainties, we proposed the VAE-kdtree attack model which eliminates the high dependency between selected training samples and the target model. It can not only save redundant computation, but also extract critical boundaries more accurately in image classification. This VAE-kdtree model has shown to achieve around 90% similarity on MNIST and around 80% similarity on MNIST-Fashion with a target Convolutional Network Model and a target Support Vector Machine Model. The performance of this VAE-kdtree model could be further improved by adopting higher dimension space of the kdtree.

Citation Download Citation

Tianqi Wen, Haibo Hu, and Huadi Zheng "An extraction attack on image recognition model using VAE-kdtree model", Proc. SPIE 11766, International Workshop on Advanced Imaging Technology (IWAIT) 2021, 117660N (13 March 2021); https://doi.org/10.1117/12.2590844

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available