Comments (2)
Update some new experiment result:
I use the Feature Squeezing on the vgg-face model with cw2 attack, and the result is 68% TPR on the median_filter_4_4. Better than the result bit_depth. It seems like normal.
But I encountered something strange, when I only use bit_depth_1 bit_depth_4 bit_depth_8 these three squeezer respectively. All of their threshold trained result is 0.000000. All the distance is 0 in the list returned from get_distance function.
Is that the zero threshold result is reasonable? Where did I give the wrong parameters?
from evademl-zoo.
Hi @stuking , thanks for your interest in our work.
The adversarial examples in the training set is not required, because we would select the threshold value using legitimate examples only. But there's no harm to include adversarial examples.
A threshold value is picked so that the false positive rate on legitimate examples in training set is not larger than a specified value, such as 5%. A zero threshold value usually means the squeezing method barely changes the model prediction on legitimate examples --less than 5% legitimate examples have distance >0. It would be a great squeezing method if the distance is large for adversarial examples. But it could be useless if the distance of adversarial examples is often zero (e.g. an identity function). Please read our paper for more details.
We have changed the name of filters at some point. Please use "median_filter_2_2" instead of "median_smoothing_2". You can find more examples of the filter names on this page: https://github.com/mzweilin/EvadeML-Zoo/blob/master/Reproduce_FeatureSqueezing.md
I believe we can close the issue now.
Best,
-Weilin
from evademl-zoo.
Related Issues (17)
- image preprocessing HOT 2
- How can I use custom models rather than pre-trained models? HOT 1
- About the python version and core dumped error HOT 3
- ImportError HOT 2
- adversarial MNIST sample
- import error in main.py HOT 1
- ModuleNotFoundError: No module named 'cleverhans' HOT 2
- FileNotFoundError HOT 1
- the wrong densenet package
- what is difference between listed pretrained models HOT 1
- "releases" folder not found. HOT 2
- Where is pretrain imagenet model weight like inception_v3? HOT 2
- pre-generated adversary examples's original label HOT 1
- Dependency broken issue HOT 1
- How to reproduce the ImageNet results HOT 5
- Optional parameters HOT 4
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 evademl-zoo.