Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examples
Abstract
We present DeClaW, a system for detecting, classifying, and warning of adversarial inputs presented to a classification neural network. In contrast to current state-of-the-art methods that, given an input, detect whether an input is clean or adversarial, we aim to also identify the types of adversarial attack (e.g., PGD, Carlini-Wagner or clean). To achieve this, we extract statistical profiles, which we term as anomaly feature vectors, from a set of latent features. Preliminary findings suggest that AFVs can help distinguish among several types of adversarial attacks (e.g., PGD versus Carlini-Wagner) with close to 93% accuracy on the CIFAR-10 dataset. The results open the door to using AFV-based methods for exploring not only adversarial attack detection but also classification of the attack type and then design of attack-specific mitigation strategies.
Cite
@article{arxiv.2107.00561,
title = {Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examples},
author = {Nelson Manohar-Alers and Ryan Feng and Sahib Singh and Jiguo Song and Atul Prakash},
journal= {arXiv preprint arXiv:2107.00561},
year = {2021}
}
Comments
ICML 2021 workshop on A Blessing in Disguise: The Prospects and Perils of Adversarial Machine Learning