@inproceedings{64c9d26928fb48ad94b22473c2f09b30,
title = "Random ensemble of locally optimum detectors for detection of adversarial examples",
abstract = "Deep neural networks achieve state-of-the-art performance for several image classification problems but have been shown to be easily fooled by adversarial perturbations which slightly modify a legitimate image in a specific direction and are visually indistinguishable from the original. This presents a security risk for applications such as autonomous systems. We tackle the problem of detecting such »forgeries» using a locally optimal detector which is well suited to detecting weak signal perturbations. We present a procedure for learning the forgery detector from a training set, using Gaussian Mixture Models (GMM) for modeling image patches. A random ensemble of patches is used for detection of the forgery. The reliability of our forgery detector is assessed for several image classification tasks.",
author = "Amish Goel and Pierre Moulin",
year = "2019",
month = feb,
day = "20",
doi = "10.1109/GlobalSIP.2018.8646479",
language = "English (US)",
series = "2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1189--1193",
booktitle = "2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings",
address = "United States",
note = "2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 ; Conference date: 26-11-2018 Through 29-11-2018",
}