Comments (8)
Hey Yiming, let me double check, I tried to simplify the API and might have broken something.
from backdoors101.
Hey Yiming, let me double check, I tried to simplify the API and might have broken something.
Thank you for your helps and looking forward to your results :)
from backdoors101.
I think my config for cifar confused pre-trained models, but I think simply using a fixed scale and not MGDA will work better.
from backdoors101.
I think my config for cifar confused pre-trained models, but I think simply using a fixed scale and not MGDA will work better.
Thanks for your response. I just want to make sure there is no misunderstanding. The model is trained from the scratch instead of fine-tuning on a pre-trained benign model and we adopt the same settings used in your codes. In this case, why we can not reproduce your results?
from backdoors101.
Hey, I actually never tested CIFAR as we did Imagenet in the paper so I didn't check it thoroughly, sorry.
I believe it's fixed now. I added a threshold to start poisoning after normal loss reaches 1.0 (we have a fancier idea in the paper on Figure 10 but I think this one works well). I also updated the parameters for the CIFAR run. Can you please let me know if it fixed your issue.
from backdoors101.
I think my config for cifar confused pre-trained models, but I think simply using a fixed scale and not MGDA will work better.
hello, I am also try to reproduce your experiment, can you provide your fixed scale that you get?
Thank you!
from backdoors101.
I guess you can just set it to 0.9
from backdoors101.
I guess you can just set it to 0.9
Thank you for your fast reply!
Here you mean
clean:backdoor = 1 : 0.9 or clean:backdoor = 0.1 : 0.9 ?
Thank you!
from backdoors101.
Related Issues (20)
- How do I perform semantic backdoor attack? HOT 5
- Where can you find the dataset for training of model? HOT 1
- "Cifar is downloaded using PyTorch": Is there a way to insert own image into the Cifar10 dataset? HOT 3
- How do you measure the effectiveness of the attack? HOT 2
- Questions regarding evading Neural Cleanse HOT 1
- Questions Regarding the code Implementation HOT 1
- Question about parameter fl_eta in cifar_fed.yaml HOT 2
- Question regarding federated experiment with multiple GPUs on one node (machine) HOT 2
- Questions about low accuracy of Test_backdoor_True HOT 2
- Questions about fl_task.update_global_model HOT 3
- dose I need to write the multi_mnist_params.yaml if I want to run the multi_mnist task? HOT 2
- about the PIPA dataset HOT 1
- can't get a clear result HOT 1
- Bug in save_model function HOT 1
- pip install failing HOT 2
- Running FL
- General questions regarding the framework HOT 8
- Enquiries about the attacks HOT 2
- Problem saving results into "runs" and "saved_models" HOT 2
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 backdoors101.