Comments (2)
The code of this perturbation generation is from the paper we replicate and we did not change that part.
The fooling rate does not influence the training process of backdoor model much. What we observed is that even if the fooling rate is low, the attack process can still be successful. I remember when we run the script it is also low, but we found that the perturbation actually works in the attack process. And you can observe that the perturbation itself looks like adding a filter to images by your eyes. Hopes this information can help you. I suggest you to run the attack with perturbation you get first.
from backdoorbench.
Thanks for your answer. It really solves my confusion. Thanks again for your great work!
from backdoorbench.
Related Issues (20)
- Errors when we execute shell script
- LC attack source HOT 1
- missing resource
- Cannot generate poison data in SSBA algorithm HOT 5
- 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
- About Missing Clean Model for TrojanNN Attack Implementation HOT 2
- RuntimeError: DataLoader worker (pid(s) 35464) exited unexpectedly HOT 1
- How can i use the Vit model.pt ? HOT 1
- can not generate trigger using low frequency attack for resnet18 HOT 1
- low test acc in the lira attack experimental HOT 1
- Is there an error in the calculation of outlier score in spectral.py HOT 2
- Model Zoo and Onedrive link cannot be accessed HOT 4
- CTRL
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.