Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency
Shasha Li, Shitong Zhu, Sudipta Paul, Amit Roy-Chowdhury, Chengyu Song, Srikanth Krishnamurthy, Ananthram Swami, Kevin S Chan
Abstract
There has been a recent surge in research on adversarial perturbations that defeat Deep Neural Networks (DNNs); most of these attacks target object classifiers. Inspired by the observation that humans are able to recognize objects that appear out of place in a scene or along with other unlikely objects, we augment the DNN with a system that learns context consistency rules during training and checks for the violations of the same during testing. In brief, our approach builds a set of autoencoders, one for each object class, appropriately trained so as to output a discrepancy between the input and output if a perturbation was added to the sample and trigger context violation. Experiments on PASCAL VOC and MS COCO show that our method effectively detects various adversarial attacks and achieves high ROC-AUC (over 0.95 in most cases); this corresponds to over 20-45 % improvement over a baseline context agnostic method."
BibTeX
@inproceedings{eccv2020_connectingthedot,
title = {Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency},
author = {Shasha Li and Shitong Zhu and Sudipta Paul and Amit Roy-Chowdhury and Chengyu Song and Srikanth Krishnamurthy and Ananthram Swami and Kevin S Chan},
booktitle = {ECCV 2020},
year = {2020}
}