DeepAI AI Chat
Log In Sign Up

Where Classification Fails, Interpretation Rises

by   Chanh Nguyen, et al.

An intriguing property of deep neural networks is their inherent vulnerability to adversarial inputs, which significantly hinders their application in security-critical domains. Most existing detection methods attempt to use carefully engineered patterns to distinguish adversarial inputs from their genuine counterparts, which however can often be circumvented by adaptive adversaries. In this work, we take a completely different route by leveraging the definition of adversarial inputs: while deceiving for deep neural networks, they are barely discernible for human visions. Building upon recent advances in interpretable models, we construct a new detection framework that contrasts an input's interpretation against its classification. We validate the efficacy of this framework through extensive experiments using benchmark datasets and attacks. We believe that this work opens a new direction for designing adversarial input detection methods.


page 1

page 2

page 4

page 6


Interpretable Deep Learning under Fire

Providing explanations for complicated deep neural network (DNN) models ...

EagleEye: Attack-Agnostic Defense against Adversarial Inputs (Technical Report)

Deep neural networks (DNNs) are inherently vulnerable to adversarial inp...

An Adversarial Robustness Perspective on the Topology of Neural Networks

In this paper, we investigate the impact of neural networks (NNs) topolo...

Adversarial Machine Learning: An Interpretation Perspective

Recent years have witnessed the significant advances of machine learning...

Adaptive Perturbation Generation for Multiple Backdoors Detection

Extensive evidence has demonstrated that deep neural networks (DNNs) are...

Detecting and Recovering Adversarial Examples: An Input Sensitivity Guided Method

Deep neural networks undergo rapid development and achieve notable succe...

Adversary Detection in Neural Networks via Persistent Homology

We outline a detection method for adversarial inputs to deep neural netw...