On Visible Adversarial Perturbations & Digital Watermarking
Author:
- Jamie HayesJHJamie Hayes
- 1 June 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1678-16787
Abstract
Given a machine learning model, adversarial perturbations transform images such that the model's output is classified as an attacker chosen class. Most research in this area has focused on adversarial perturbations that are imperceptible to the human eye. However, recent work has considered attacks that are perceptible but localized to a small region of the image. Under this threat model, we discuss both defenses that remove such adversarial perturbations, and attacks that can bypass these defenses.Keywords
This publication has 8 references indexed in Scilit:
- Adversarial Examples Are Not Easily Detected2017
- Towards Evaluating the Robustness of Neural Networks2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Improving the Robustness of Deep Neural Networks via Stability Training2016
- Adversarial Diversity and Hard Positive Generation2016
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks2016
- The Limitations of Deep Learning in Adversarial Settings2016
- An Image Inpainting Technique Based on the Fast Marching MethodJournal of Graphics Tools, 2004