Comments (2)
During training we perform random start, i.e. we add a random perturbation before the first PGD step. During eval, we test PGD from multiple random starts and keep the worst. That is we run a full PGD attack from (say) 20 different random starts and consider an classifier successful only if it was not fooled by any of these 20 attacks. As you can see, an attack that uses a bunch of restarts reduces the robust accuracy by a few percent compared to a single start attack. Using a random start during training is not essential, you can set random_start
to false
and you will get comparable results.
from mnist_challenge.
Thanks!
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
- Why epsilon can be larger than 1? HOT 6
- 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
- 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.