Comments (2)
Sorry for confusion, clean_model.pth is actually the clean model trained without backdoor attack. For example, if you want to attack preactresnet18 on cifar10, then the clean_model.pt should be weight of preactresnet18 trained on cifar10.
Here is the link contains many clean_model.pth : https://drive.google.com/drive/folders/1lnCObVBIUTSlLWIBQtfs_zi7W8yuvR-2?usp=share_link
from backdoorbench.
Thank you very much for your response; this project has truly been a great help to me, and I appreciate your work and effort once again!
As mentioned before, I am trying to conduct a new defense research based on your project. In experiments using the ResNet-18 architecture and applied to two different datasets, I have tested seven different backdoor attack methods and achieved some results. However, I believe one of the key challenges in backdoor attack defense is determining whether a model has been implanted with a backdoor. If we cannot accurately determine this, we may need to test various defense methods on clean models to ensure they do not negatively affect clean models. But currently, based on your project, I feel that implementing this test seems somewhat difficult.
I would like to ask if you have any good suggestions or methods to help me complete this experiment? I would be extremely grateful for any guidance!
from backdoorbench.
Related Issues (20)
- v2.0 run scripts
- Results for Tiny Imagenet HOT 1
- A data loading problem of LC attack HOT 2
- fine-pruning is missing HOT 1
- Bugs in WaNet All2All Attack HOT 1
- the data of leaderboard(asr of blended to nad) HOT 2
- Attack my own datasets made with videos. HOT 1
- Errors when we execute shell script
- LC attack source HOT 1
- missing resource
- Cannot generate poison data in SSBA algorithm HOT 5
- can not generate trigger for low frequency attack HOT 2
- Target Class of Label-Consistent in the Google Drive
- 您好,很敬佩该工作对于后门攻击的总结。 想请问下为什么 v1 里的 ft_attack 频域后门攻击 在v2 里被移除了呢
- How to use this library in an incremental manner? HOT 1
- Implementation issue with ANP HOT 3
- Poison Index Selection - Clean label case HOT 3
- bpp attack source HOT 2
- Backdoor OneDrive Access Unavailable 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 backdoorbench.