Comments (5)
Could you provide a full log here?
For Neural Cleanse, it's generating backdoors for each class, and see if any backdoor is an outlier, which tend to be the poisoned class.
I'll investigate the fine-pruning issue.
from trojanzoo.
I just test on CIFAR10 with ResNet18_comp and it works, which is the setting we use in the paper (though the console print is a little messy...) .
I'll later check MNIST.
from trojanzoo.
Yes, this error happened only when I test on MNIST dataset. May this message will help.
from trojanzoo.
Sorry for the long delay. I'm busy doing other projects and update trojanzoo docs.
I've located the problem about this. The current codes assume _model.pool
to be a AdaptiveAvgPool2d((1,1))
that transforms tensor shape from [N, C, H, W]
to [N, C, 1, 1]
.
However, MNIST actually has a MaxPool2d(2)
instead, it transforms [4, 64, 24, 24]
to [4, 64, 12, 12]
. And finally after flatten
, the [12, 12]
are multiplied to the channel 64
to be 9216=64*12*12
, which cause the index out of range.
I'll fix this soon.
from trojanzoo.
Just to note that I recently make many breaking changes. --pretrain
to --pretrained
and --random_init
to --mark_random_init
for example.
You may check the docs (have finished most part) for new apis. Sadly concrete attacks and defenses docs haven't been finished yet.
https://ain-soph.github.io/trojanzoo/
from trojanzoo.
Related Issues (20)
- BackdoorAttack class has no argument for source_class HOT 1
- Low effective loading in get_class_subset function HOT 1
- Install newest version fail HOT 1
- Using a custom model HOT 4
- RuntimeError: Dataset not found or corrupted. You can use download=True to download it HOT 10
- Clean label attack accuracy is wrong HOT 5
- In new push model path is not working HOT 1
- badnet folder information HOT 1
- [Error] When I test Neural Cleanse i got a error HOT 2
- Is it possible to apply methods to graph? HOT 6
- Input aware dynamic backdoor error HOT 5
- trojanvision.datasets.ImageFolder HOT 1
- Possible bug: target_class not changed when computing ASR for reversed triggers HOT 2
- problem about saving the intermediate results and config problem HOT 6
- strange mark saved HOT 2
- Hyperparameters for training Resnet18 on CIFAR10? HOT 1
- STRIP implementation doesn't match original codebase HOT 1
- Attack saving and loading is not working HOT 2
- Comp version of networks HOT 2
- Unable to Access Triggered Dataset in BadNet Attack HOT 5
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 trojanzoo.