DeepAI AI Chat
Log In Sign Up

Deep Neural Rejection against Adversarial Examples

by   Angelo Sotgiu, et al.
Universita Cagliari

Despite the impressive performances reported by deep neural networks in different application domains, they remain largely vulnerable to adversarial examples, i.e., input samples that are carefully perturbed to cause misclassification at test time. In this work, we propose a deep neural rejection mechanism to detect adversarial examples, based on the idea of rejecting samples that exhibit anomalous feature representations at different network layers. With respect to competing approaches, our method does not require generating adversarial examples at training time, and it is less computationally demanding. To properly evaluate our method, we define an adaptive white-box attack that is aware of the defense mechanism and aims to bypass it. Under this worst-case setting, we empirically show that our approach outperforms previously-proposed methods that detect adversarial examples by only analyzing the feature representation provided by the output network layer.


page 5

page 6

page 7


Detecting Adversarial Examples via Key-based Network

Though deep neural networks have achieved state-of-the-art performance i...

One Man's Trash is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examples

Modern image classification systems are often built on deep neural netwo...

Adversarial Fine-tuning for Backdoor Defense: Connect Adversarial Examples to Triggered Samples

Deep neural networks (DNNs) are known to be vulnerable to backdoor attac...

Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub Humanoid

Deep neural networks have been widely adopted in recent years, exhibitin...

Adversarial Examples Detection and Analysis with Layer-wise Autoencoders

We present a mechanism for detecting adversarial examples based on data ...

FADER: Fast Adversarial Example Rejection

Deep neural networks are vulnerable to adversarial examples, i.e., caref...

Detecting Adversarial Examples through Nonlinear Dimensionality Reduction

Deep neural networks are vulnerable to adversarial examples, i.e., caref...

Code Repositories