When Not to Classify: Detection of Reverse Engineering Attacks on DNN Image Classifiers
Computer Vision and Pattern Recognition
2018-11-08 v1 Machine Learning
Machine Learning
Abstract
This paper addresses detection of a reverse engineering (RE) attack targeting a deep neural network (DNN) image classifier; by querying, RE's aim is to discover the classifier's decision rule. RE can enable test-time evasion attacks, which require knowledge of the classifier. Recently, we proposed a quite effective approach (ADA) to detect test-time evasion attacks. In this paper, we extend ADA to detect RE attacks (ADA-RE). We demonstrate our method is successful in detecting "stealthy" RE attacks before they learn enough to launch effective test-time evasion attacks.
Cite
@article{arxiv.1811.02658,
title = {When Not to Classify: Detection of Reverse Engineering Attacks on DNN Image Classifiers},
author = {Yujia Wang and David J. Miller and George Kesidis},
journal= {arXiv preprint arXiv:1811.02658},
year = {2018}
}