Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > comp.programming.threads > #3853 > unrolled thread

Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks

Back to article view | Back to comp.programming.threads

Contents

  Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks rami18 <coco@coco.com> - 2017-07-26 14:39 -0400

#3853 — Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks

Hello...

Read this:

Adversarial perturbations are not "natural" images. They are regular and 
just don't occur in nature. This is possibly the most important 
unexplained aspect of neural networks and machine learning and it is 
being studied as a security or safety problem. What is some evil person 
misleads a machine intelligence? What if a self driving car is made to 
crash because an adversarial signal is injected into the video feed?

Here is an interesting paper about it:

Distillation as a Defense to Adversarial Perturbations against Deep 
Neural Networks

https://arxiv.org/pdf/1511.04508.pdf




Thank you,
Amine Moulay Ramdane,

[toc] | [standalone]

Back to top | Article view | comp.programming.threads

csiph-web