search

chetanniloor / De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks

The most critical downside to AI is that its inefficiency is directly related to its data quality. Presently there are very few methods available that are used to protect the data from being attacked in the real time applications. But there is no commonplace in terms of defence technology that is being used for various types of attacks, in these situations the need for a generic method is highly needed for defending against those poisoning attacks, so we have come up with the defence technique that is called as De-Pois Defence method
3 stars 0 forks source link

Can not find the file "p_labels.csv" #1

Open Dangxc opened 1 year ago

Dangxc commented 1 year ago

OSError: p_labels.csv not found. And how to generate the file “p_labels.csv‘’？

Meet19aug commented 1 year ago

I executed "mnist_direct.py" as well as "mnist_generative.py" but it just created result of that mentioned paper not the csv file can you find a way to do it?

do you have p_data.csv file?

I got error at following line of code "def poi_data(poison_rate): poison_number = int(poison_rate * 50000) poisoned_x_data = np.load("pdata%d.npy"%(poison_number)). <----- poisoned_y_data = np.load("plabel%d.npy"%(poison_number))". <-------

Dangxc commented 1 year ago

For the p_data.csv and p_labels.csv, I have contacted the author, he gave me a reply:

“You can run mnist_direct.py and obtain the generate poisoned data directly. For instance, in line 151 of mnist_direct.py, the method begins to generate poisoned data and the variable 'data_p' and 'label_p 're the final poisoned data and the corresponding label. After obtaining the poisoned data and the label, you can save them in "npy" format."

But I can’t save them in 'npy' format, could you get it follow the way from the author?

Meet19aug commented 1 year ago

I will try and tell you as soon as possible can we connect on LinkedIn for easy communication? https://www.linkedin.com/in/meeet

Regards Meet Patel On Sat, Apr 15, 2023, 11:34 AM Dangxc @.***> wrote:

For the p_data.csv and p_labels.csv, I have contacted the author, he gave me a reply:

“You can run mnist_direct.py and obtain the generate poisoned data directly. For instance, in line 151 of mnist_direct.py, the method begins to generate poisoned data and the variable 'data_p' and 'label_p 're the final poisoned data and the corresponding label. After obtaining the poisoned data and the label, you can save them in "npy" format."

But I can’t save them in 'npy' format, could you get it follow the way from the author?

— Reply to this email directly, view it on GitHub https://github.com/chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1#issuecomment-1509556289, or unsubscribe https://github.com/notifications/unsubscribe-auth/AOVVA3OJKMZTMUDUPV6SY2TXBI25JANCNFSM6AAAAAAWQHGWVM . You are receiving this because you commented.Message ID: <chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1/1509556289 @github.com>

Dangxc commented 1 year ago

I'm sorry I don't have linkedin account, we can contact through email, I have sent an email to your gmail, please pay attention to check your Google email.

Xiaocui Dang

@. | ---- Replied Message ---- | From | Meet @.> | | Date | 4/15/2023 17:54 | | To | @.> | | Cc | @.> , @.***> | | Subject | Re: [chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks] Can not find the file "p_labels.csv" (Issue #1) |

I will try and tell you as soon as possible can we connect on LinkedIn for easy communication? https://www.linkedin.com/in/meeet

Regards Meet Patel On Sat, Apr 15, 2023, 11:34 AM Dangxc @.***> wrote:

For the p_data.csv and p_labels.csv, I have contacted the author, he gave me a reply:

“You can run mnist_direct.py and obtain the generate poisoned data directly. For instance, in line 151 of mnist_direct.py, the method begins to generate poisoned data and the variable 'data_p' and 'label_p 're the final poisoned data and the corresponding label. After obtaining the poisoned data and the label, you can save them in "npy" format."

But I can’t save them in 'npy' format, could you get it follow the way from the author?

— Reply to this email directly, view it on GitHub https://github.com/chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1#issuecomment-1509556289, or unsubscribe https://github.com/notifications/unsubscribe-auth/AOVVA3OJKMZTMUDUPV6SY2TXBI25JANCNFSM6AAAAAAWQHGWVM . You are receiving this because you commented.Message ID: <chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1/1509556289 @github.com>

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

Meet19aug commented 1 year ago

Hello, here is the code that help me to create the file while executing the code and saving it with .npy format. python code is "np.save('p_data_15000.npy', data_p.asnumpy()) " and same for label file.

Regards, Meet

On Mon, Apr 17, 2023 at 8:11 AM Dangxc @.***> wrote:

I'm sorry I don't have linkedin account, we can contact through email, I have sent an email to your gmail, please pay attention to check your Google email.

Xiaocui Dang

@. | ---- Replied Message ---- | From | Meet @.> | | Date | 4/15/2023 17:54 | | To | @.> | | Cc | @.> , @.***> | | Subject | Re: [chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks] Can not find the file "p_labels.csv" (Issue #1) |

I will try and tell you as soon as possible can we connect on LinkedIn for easy communication? https://www.linkedin.com/in/meeet

Regards Meet Patel On Sat, Apr 15, 2023, 11:34 AM Dangxc @.***> wrote:

For the p_data.csv and p_labels.csv, I have contacted the author, he gave me a reply:

“You can run mnist_direct.py and obtain the generate poisoned data directly. For instance, in line 151 of mnist_direct.py, the method begins to generate poisoned data and the variable 'data_p' and 'label_p 're the final poisoned data and the corresponding label. After obtaining the poisoned data and the label, you can save them in "npy" format."

But I can’t save them in 'npy' format, could you get it follow the way from the author?

— Reply to this email directly, view it on GitHub < https://github.com/chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1#issuecomment-1509556289 , or unsubscribe < https://github.com/notifications/unsubscribe-auth/AOVVA3OJKMZTMUDUPV6SY2TXBI25JANCNFSM6AAAAAAWQHGWVM

. You are receiving this because you commented.Message ID:

<chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1/1509556289 @github.com>

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

— Reply to this email directly, view it on GitHub https://github.com/chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1#issuecomment-1510607817, or unsubscribe https://github.com/notifications/unsubscribe-auth/AOVVA3LM3GDT2VHVIZRUY4DXBSUT7ANCNFSM6AAAAAAWQHGWVM . You are receiving this because you commented.Message ID: <chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1/1510607817 @github.com>