hcguoo0/fia

code for "Feature Importance-aware Transferable Adversarial Attacks"

fia's Issues

low attack success rate(攻击成功率不正常的低)

Hi!
Thanks for your contribution! But when I run the command line you mentioned in readme file
"python attack.py --model_name vgg_16 --attack_method FIAPIM --layer_name vgg_16/conv3/conv3_3/Relu --ens 30 --probb 0.7 --amplification_factor 2.5 --gamma 0.5 --Pkern_size 3 --image_size 224 --image_resize 250 --prob 0.7 --output_dir ./adv/FIAPIDIM/"
and "python verify.py --ori_path ./dataset/images/ --adv_path ./adv/FIAPIDIM/ --output_file ./log.csv".
I got adv_acc around 70%-80% and adv_succ around 20%-30%. Is there something wrong with your defulat parameter?
在运行readme里面提到的指令时，仅仅得到20%-30%的准确率，请问是否是默认参数不小心给错了呢？还是什么其他问题？

low ori_acc rate(原始精度异常低)

Hi, thanks for your contribution! But some problems arose during the process.

The ori_acc is 1.2% or 1.3%, and the adv_suc is around 60%~70%. Is there somthing wrong?

Parameter setting of resnet_v1_152

Hi, thank you for sharing the code! I'm trying to run the attack.py using resnet_v1_152, may I know the parameter setting.

There is something wrong when i run the program。

Hello,thank you very much for sharing the program.But when i run the attack.py on IncRes_V2 and Inc_v3,there is something wrong with the program.With the IncRes_V2,there is an error:ValueError: Negative dimension size caused by subtracting 5 from 3 for 'InceptionResnetV2/AuxLogits/Conv2d_2a_5x5/Conv2D' (op: 'Conv2D') with input shapes: [40,3,3,128], [5,5,128,768].And with the Inc_v3,there is an error:Tensor name "InceptionV3/AuxLogits/Conv2d_2a_3x3/BatchNorm/beta" not found in checkpoint files ./models_tf/inception_v3.ckpt
[[node save/RestoreV2 (defined at attack.py:267) ]]
Can you tell me what's wrong? Thank you very much!

其他模型的中间层参数怎么设置？

readme中只给出了vgg_16的参数，其他几个模型运行的时候怎么设置参数呢

Wondering the exact layer name

Thanks for sharing the code! I've tried to run attack.py on InceptionV3(using layer InceptionV3/InceptionV3/Mixed_5b/concat), InceptionV4(using layer InceptionV4/InceptionV4/Mixed_6f/concat) and Resnet_v1_50(using layer resnet_v1_50/block4/unit_3/bottleneck_v1/conv2/Relu), but got poor results, so could you please share the EXACT LAYER NAME you used to attack?

Hi, thanks very much for sharing these valuable codes. There still remains an issue about the used dataset.

According to the published paper, the ImageNet-Compatible dataset is used to conduct experiments. By downloading the above dataset from the website in reference [1], it is strange to find that there are only 904 images can be downloaded, rather than 1000 images illustrated in the paper. Therefore, could you please validate how many images were actually used in the experimental phase? Of course, if all 1000 images were used in your experiments, could you please share these images through Google Clouds or Baidu Clouds (urls of the missed 96 images are invalid now)?

Thanks very much!

How to craft Fig.3 in your paper?

Thanks for sharing your code. I'm reading your paper and would like to know how to craft Fig.3.

looking forward to the code

Code for Fig.3 in your paper

Hi, it seems that attack.py cannot use GPU, could you please check related codes?

在评估成功率时运行到vgg_16无报错中断

在评估成功率时运行到vgg_16无报错中断，是因为缺少什么配置文件吗？

The mid-layer parameter？

Hello，Could tell me when inception-resnet-v2 as the source model，what mid layer to be attack，I set the parameter ‘InceptionResnetV2/InceptionResnetV2/Conv2d_4a_3x3/Relu’ that follows your paper Conv_4a. But the permance is lower 10% comparing the result in your paper. So what is the mid parameter when you attack inception-resnet-v2? Thx.

About PI-FGSM

Why your code about PI-FGSM is not the same as the theory in the pape

Hi, there is a issue when I run verify.py

(0) Data loss: Unable to open table file ./models_tf/ens3_adv_inception_v3/ens3_adv_inception_v3.ckpt: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?

the model i use is ens3_adv_incetption_v3, Could you reply me?

使用其他模型中间层参数会报错

使用Inceptionv3模型的中间层参数: InceptionV3/InceptionV3/Mixed_5b/concat
运行会报错
tensorflow.python.framework.errors_impl.NotFoundError: Tensor name "InceptionV3/AuxLogits/Conv2d_2a_3x3/BatchNorm/beta" not found in checkpoint files ./models_tf/inception_v3.ckpt
[[{{node save/RestoreV2}} = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]

Problem with attacking inceptionv3 and inception resnet v2

Hi,
I met problems when attacking incepionv3 and inception resnetv2 model:

Traceback (most recent call last):
File "/home/eric/anaconda3/envs/tf12/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1334, in _do_call
return fn(*args)
File "/home/eric/anaconda3/envs/tf12/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1319, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "/home/eric/anaconda3/envs/tf12/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1407, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.NotFoundError: Tensor name "InceptionV3/AuxLogits/Conv2d_2a_3x3/BatchNorm/beta" not found in checkpo
int files ./models_tf/inception_v3.ckpt
[[{{node save/RestoreV2}} = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV
2/shape_and_slices)]]

And it seems to be related to this: cameronfabbri/Compute-Features#2

Could you please check it and tell me how to fix this? Thank you!

I have some questions

Can you tell me how to run the FIA+PITIDIM.I want to verify the data if the Table. 2.Thanks very much!

code

Hello, I'd like to ask if you have the version code reference of pytorch