Comments (6)
You are right, since valid pixel values are from 0 to 1, we clip the perturbation to that range at every step.
The value 8 that you are referring to corresponds to the CIFAR10 dataset where valid pixel values are from 0 to 255. So 8 is actually quite small.
Let me know if that does not make sense.
from mnist_challenge.
okay, thank you very much!
from mnist_challenge.
So why do you use epsilon=8/255 for CIFAR10 but epsilon=0.3 for MNIST rather than use epsilon=8/255 for both datasets? Does 0.3 for MNIST means 0.3/255? If not, why do you use such large epsilon (0.3>>8/255) on MNIST?
Please forgive me for such a stupid question. I'm a greenhand in this area.
from mnist_challenge.
We do use a different epsilon for each dataset---for MNIST we use 0.3/1 and for CIFAR10 8/255. The reason is that these datasets are quite different so the epsilon values that we can be robust to are also different. Specifically, MNIST consists of black-and-white images, so a perturbation of 0.3 cannot change a white pixel to black and vice-versa (which is why we are able to learn robust classifiers after all). In contrast, for CIFAR10, pixels lie in a wider range of values, while the image is 3-dimensional (RGB). As a result, the perturbation needed to actually change the class of an image is much smaller (in Figure 8 of https://arxiv.org/abs/1805.12152 you can see how perturbations of 0.125/1 on CIFAR10 completely change the content of the image).
from mnist_challenge.
I get it. Thank you very much!
from mnist_challenge.
Related Issues (16)
- Release Model HOT 3
- wrong implementation of CW attack HOT 3
- Any adversarial attack that sustains after resize attack? HOT 3
- What does this line do? HOT 1
- Adversarial performance for MNIST models vary widely with different random seed initializations HOT 1
- Requirements to reproduce the results
- Are there any Pytorch version of this challenge? Cause tensorflow usually has conflict with my Pytorch. HOT 2
- about version HOT 1
- (Not an issue) Request to keep the challenge open HOT 2
- Does PGD not need to perform random restart in every iterative ? Is it enough to start with random noise at FGSM? HOT 3
- Question about reproducing your results HOT 2
- For the reported results with 100 iterations, is the eps_iter/"a" value still 0.01? HOT 1
- About random restart HOT 2
- parameters for train robust adv_trained/secret networks? HOT 1
- tf.tf.Variable() seems cannot be replaced with tf.get_variable(). HOT 8
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mnist_challenge.