This repository contains experiments (and related code) for the paper 'Gradient Similarity: An Explainable Approach to Detect Adversarial Attacks against Deep Learning'. We create a gradient based white-box detector of adversarial samples for MNIST, DREBIN, CIFAR2 datasets.
-
Notifications
You must be signed in to change notification settings - Fork 0
jasjeetIM/AdversarialDetector
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Robust white-box detector for adversarial samples against deep learning
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published