Comments (2)
Hi, thanks for your interest in our work.
Yes, data normalization was not used for training a backdoored model because this is a default setting of previous research at that time in 2021. You could definitely add various data augmentation techniques (e.g. flip, random crop, or data normalization) to train your backdoored model. We would gladly point out, in this case, our NAD also achieves consistent defense performance.
from nad.
Yes, your method also achieves consistent defense performance. Thanks for your reply.
from nad.
Related Issues (17)
- RuntimeError: view size is not compatible with input tensor's size and stride HOT 1
- The reproducibility of experiments in the paper HOT 2
- What config did you use to have the model return the activations? HOT 1
- Configuration HOT 1
- Trojan trigger(/NAD/trigger/best_square_trigger_cifar10.npz) not effective HOT 2
- is it possible to transfer NAD to other models?( for example resnet18) HOT 3
- Wheather the so-called attebtion distillation machanism work? HOT 2
- A question when analyzing the code
- How to get the teacher model? HOT 3
- Do you provide the code to fine-tune the student model? HOT 5
- the loss function is not useful in the experiment? HOT 7
- How to train CL and Refool backdoored model? HOT 1
- Results of BadNet and Fine-tuning HOT 10
- performance on GTSRB HOT 1
- How does the attention loss work HOT 1
- A few question HOT 1
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 nad.