When Not to Classify: Detection of Reverse Engineering Attacks on DNN Image Classifiers

Yujia Wang; David J. Miller; George Kesidis

ICASSP 2019accepted0 citations

When Not to Classify: Detection of Reverse Engineering Attacks on DNN Image Classifiers

Yujia Wang, David J. Miller, George Kesidis

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.

BibTeX

@inproceedings{icassp2019_whennottoclassif,
  title = {When Not to Classify: Detection of Reverse Engineering Attacks on DNN Image Classifiers},
  author = {Yujia Wang and David J. Miller and George Kesidis},
  booktitle = {ICASSP 2019},
  year = {2019}
}