backdoor_federated_learning

backdoor_federated_learning copied to clipboard

Backdoor accuracy can't reach 100%

1

I have some problems when i am trying to reproduce the experiment results in this paper. I pull the source code and run it with params.yaml after setting is_poison=True and...

ybdai7

Low accuracy: Even without poisoning, the accuracy is only about 10%

11

Even with "is_poison"=false, the accuracy is only about 10%. When "is_poison"=true and batch_size=264, I get the results as follows: When there are adversaries, accuracy of backdoor is about 100%，accuracy without...

Juli-Eyre

Runtime Error

13

when i run **_python training.py --params utils/params.yaml_**, raised a error :

IUUI11

A program problem

2

It seems to me that poison_dataset() didn't poison the data, it just sampled 64 images 200 times and required them not to be images from "posion_image" and "poison_images_test". But what...

mumu029

Help if you can,thinks.

2

I would like to run your code. Could you tell me which Python packages and their respective versions are required to execute it? 

liangguomin

Corpus parsed dataset disappear

7

Guncuke

不同版本的pytorch会对实验结果有影响吗

muczhz

corpus database

2

Does anyone have this corpus database？Could you please send me a copy? Thx. My email address is: [[email protected]](mailto:[email protected])

2524434293

Bumps [torch](https://github.com/pytorch/pytorch) from 1.0 to 2.2.0. Release notes Sourced from torch's releases. PyTorch 2.2: FlashAttention-v2, AOTInductor PyTorch 2.2 Release Notes Highlights Backwards Incompatible Changes Deprecations New Features Improvements Bug fixes...

dependabot[bot]