Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain

by   Jinyu Tian, et al.

Deep neural networks (DNNs) have been shown to be vulnerable against adversarial examples (AEs), which are maliciously designed to cause dramatic model output errors. In this work, we reveal that normal examples (NEs) are insensitive to the fluctuations occurring at the highly-curved region of the decision boundary, while AEs typically designed over one single domain (mostly spatial domain) exhibit exorbitant sensitivity on such fluctuations. This phenomenon motivates us to design another classifier (called dual classifier) with transformed decision boundary, which can be collaboratively used with the original classifier (called primal classifier) to detect AEs, by virtue of the sensitivity inconsistency. When comparing with the state-of-the-art algorithms based on Local Intrinsic Dimensionality (LID), Mahalanobis Distance (MD), and Feature Squeezing (FS), our proposed Sensitivity Inconsistency Detector (SID) achieves improved AE detection performance and superior generalization capabilities, especially in the challenging cases where the adversarial perturbation levels are small. Intensive experimental results on ResNet and VGG validate the superiority of the proposed SID.



There are no comments yet.


page 1

page 2

page 3

page 4


Adversarial Detector with Robust Classifier

Deep neural network (DNN) models are wellknown to easily misclassify pre...

Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality

Deep Neural Networks (DNNs) have recently been shown to be vulnerable ag...

When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signatures

State-of-the-art deep neural networks (DNNs) are highly effective in sol...

Spatially transformed adversarial examples

Recent studies show that widely used deep neural networks (DNNs) are vul...

Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classification

Deep neural networks (DNNs) have transformed several artificial intellig...

ML-LOO: Detecting Adversarial Examples with Feature Attribution

Deep neural networks obtain state-of-the-art performance on a series of ...

EAD: an ensemble approach to detect adversarial examples from the hidden features of deep neural networks

One of the key challenges in Deep Learning is the definition of effectiv...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.