Comments (5)
Could you please provide more information? We do not find the same problem when we use it...
from backdoorbench.
python ./attack/badnet_attack.py --yaml_path ../config/attack/badnet/tiny.yaml --dataset tiny --dataset_path ../data
That is the command I used.
Thanks for replying
from backdoorbench.
I try your command, no error found. Maybe you changed some code?
2022-12-16:13:51:59 [INFO ] [badnet_attack.py:146] Getting git info fails.
2022-12-16:13:51:59 [INFO ] [dataset_and_transform_generate.py:206] save the speed up matrix data for train at ../data/tiny
2022-12-16:13:52:33 [INFO ] [dataset_and_transform_generate.py:206] save the speed up matrix data for test at ../data/tiny
2022-12-16:13:52:36 [INFO ] [bd_dataset.py:51] dataset must have NO transform in BOTH image and label !
pre-process bd dataset: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 100000/100000 [00:14<00:00, 6798.00it/s]
2022-12-16:13:52:53 [INFO ] [bd_dataset.py:51] dataset must have NO transform in BOTH image and label !
pre-process bd dataset: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10000/10000 [00:01<00:00, 6866.35it/s]
2022-12-16:13:52:55 [INFO ] [backdoor_generate_pindex.py:35] Reminder: plz note that if p_num or pratio exceed the number of possible candidate samples
then only maximum number of samples will be applied
2022-12-16:13:52:55 [INFO ] [backdoor_generate_pindex.py:36] Reminder: priority p_num > pratio, and choosing fix number of sample is prefered if possible
2022-12-16:13:52:55 [INFO ] [backdoor_generate_pindex.py:61] poison num:10000.0,real pratio:0.1
2022-12-16:13:52:55 [INFO ] [bd_dataset.py:51] dataset must have NO transform in BOTH image and label !
pre-process bd dataset: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 100000/100000 [00:16<00:00, 6229.53it/s]
2022-12-16:13:53:14 [INFO ] [backdoor_generate_pindex.py:35] Reminder: plz note that if p_num or pratio exceed the number of possible candidate samples
then only maximum number of samples will be applied
2022-12-16:13:53:14 [INFO ] [backdoor_generate_pindex.py:36] Reminder: priority p_num > pratio, and choosing fix number of sample is prefered if possible
2022-12-16:13:53:14 [INFO ] [backdoor_generate_pindex.py:61] poison num:9950.0,real pratio:0.995
2022-12-16:13:53:14 [INFO ] [bd_dataset.py:51] dataset must have NO transform in BOTH image and label !
pre-process bd dataset: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10000/10000 [00:02<00:00, 4197.16it/s]
from backdoorbench.
Actually I have the same issue here. I did not modify any code about tiny imagenet and the tiny imagenet i used was downloaded by the sh/timagenet_download.sh
I think there is something wrong that the poison num is 0 in his case.
from backdoorbench.
@fdszy I found a solution to deal with it. Change the target class from 0 to 9 could solve this problem when I was trying the default settings (PreActResNet Tiny)
The reason it fails could be something wrong with the default setting in backdoor_generate_pindex.py line 37, the default setting for pidx. (Actually the reason might not be that accurate, but I do solve the problem by doing so)
Thank you for creating all these codes. We will increase your citation count if our paper got published!
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
- About Missing Clean Model for TrojanNN Attack Implementation 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 backdoorbench.