Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistency

TL;DR

This paper introduces Argos, a multi-view inconsistency detector that identifies adversarial images by amplifying and detecting discrepancies between the true content and added perturbations, significantly improving detection accuracy and robustness.

Contribution

The paper proposes a novel multi-view detection method using autoregressive generation to reveal inconsistencies in adversarial images, outperforming existing detectors.

Findings

Argos outperforms existing detectors in accuracy and robustness.

Amplification of discrepancies enhances adversarial detection.

Effective against six well-known adversarial attacks.

Abstract

In the evasion attacks against deep neural networks (DNN), the attacker generates adversarial instances that are visually indistinguishable from benign samples and sends them to the target DNN to trigger misclassifications. In this paper, we propose a novel multi-view adversarial image detector, namely Argos, based on a novel observation. That is, there exist two "souls" in an adversarial instance, i.e., the visually unchanged content, which corresponds to the true label, and the added invisible perturbation, which corresponds to the misclassified label. Such inconsistencies could be further amplified through an autoregressive generative approach that generates images with seed pixels selected from the original image, a selected label, and pixel distributions learned from the training data. The generated images (i.e., the "views") will deviate significantly from the original one if the label is adversarial, demonstrating inconsistencies that Argos expects to detect. To this end, Argos first amplifies the discrepancies between the visual content of an image and its misclassified label induced by the attack using a set of regeneration mechanisms and then identifies an image as adversarial if the reproduced views deviate to a preset degree. Our experimental results show that Argos significantly outperforms two representative adversarial detectors in both detection accuracy and robustness against six well-known adversarial attacks. Code is available at: https://github.com/sohaib730/Argos-Adversarial_Detection