An Adversarial Approach for Explaining the Predictions of Deep Neural Networks

by   Arash Rahnama, et al.

Machine learning models have been successfully applied to a wide range of applications including computer vision, natural language processing, and speech recognition. A successful implementation of these models however, usually relies on deep neural networks (DNNs) which are treated as opaque black-box systems due to their incomprehensible complexity and intricate internal mechanism. In this work, we present a novel algorithm for explaining the predictions of a DNN using adversarial machine learning. Our approach identifies the relative importance of input features in relation to the predictions based on the behavior of an adversarial attack on the DNN. Our algorithm has the advantage of being fast, consistent, and easy to implement and interpret. We present our detailed analysis that demonstrates how the behavior of an adversarial attack, given a DNN and a task, stays consistent for any input test data point proving the generality of our approach. Our analysis enables us to produce consistent and efficient explanations. We illustrate the effectiveness of our approach by conducting experiments using a variety of DNNs, tasks, and datasets. Finally, we compare our work with other well-known techniques in the current literature.


page 3

page 7

page 12

page 13

page 18

page 19

page 21

page 22


NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks

Powerful adversarial attack methods are vital for understanding how to c...

ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models

Deep neural networks (DNNs) are one of the most prominent technologies o...

Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions

Explaining predictions of deep neural networks (DNNs) is an important an...

Imperceptible Adversarial Attack on Deep Neural Networks from Image Boundary

Although Deep Neural Networks (DNNs), such as the convolutional neural n...

Peeking inside the Black Box: Interpreting Deep Learning Models for Exoplanet Atmospheric Retrievals

Deep learning algorithms are growing in popularity in the field of exopl...

Backdoor Attack Detection in Computer Vision by Applying Matrix Factorization on the Weights of Deep Networks

The increasing importance of both deep neural networks (DNNs) and cloud ...

Learning to Abstain via Curve Optimization

In practical applications of machine learning, it is often desirable to ...

Please sign up or login with your details

Forgot password? Click here to reset