Closed Brownchen closed 3 years ago
Hi! Thanks for reaching out. The sensitive data can be selected any way you choose - for the CIFAR and MNIST domains I selected an entire class and then had two test dataloaders, one including the sensitive class test data and one including the rest of the test data. To test the membership inference attack success I used a small random selection of training instances as sensitive data.
The Amnesiac ML Evaluation.ipynb file is the testing that we did for figure 7 in the paper, but looking at it right now it's a big buggy. I'll fix it later today and let you know when it's updated.
Thanks!
-Laura Graves
The github isn't the entire code base that we used, I hadn't included a full testing and training cycle
On Wed, Nov 25, 2020 at 2:17 AM Brown Chen notifications@github.com wrote:
Thank you for publishing the code. It's a great attempt for machine unlearning. By the way, how do you select the sensitive data during the unlearning process and I can't find the corresponding code in 'Amnesiac ML Evaluation.ipynb'. I want to reproduce the model accuracy on the target and non-target data. Looking forward to your reply!
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/lmgraves/AmnesiacML/issues/1, or unsubscribe https://github.com/notifications/unsubscribe-auth/AH2MZMUF5Y4NA5ONHMHA5BLSRSVQTANCNFSM4UCACK7A .
Thank you for your reply! I do have some problems with the implementation of trainloder and testloader. Could you please publish the entire code or just send it to my email < brownchen7s@gmail.com> ?
Thanks a lot!
Laura Graves notifications@github.com 于2020年11月25日周三 下午10:01写道:
Hi! Thanks for reaching out. The sensitive data can be selected any way you choose - for the CIFAR and MNIST domains I selected an entire class and then had two test dataloaders, one including the sensitive class test data and one including the rest of the test data. To test the membership inference attack success I used a small random selection of training instances as sensitive data.
The Amnesiac ML Evaluation.ipynb file is the testing that we did for figure 7 in the paper, but looking at it right now it's a big buggy. I'll fix it later today and let you know when it's updated.
Thanks!
-Laura Graves
The github isn't the entire code base that we used, I hadn't included a full testing and training cycle
On Wed, Nov 25, 2020 at 2:17 AM Brown Chen notifications@github.com wrote:
Thank you for publishing the code. It's a great attempt for machine unlearning. By the way, how do you select the sensitive data during the unlearning process and I can't find the corresponding code in 'Amnesiac ML Evaluation.ipynb'. I want to reproduce the model accuracy on the target and non-target data. Looking forward to your reply!
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/lmgraves/AmnesiacML/issues/1, or unsubscribe < https://github.com/notifications/unsubscribe-auth/AH2MZMUF5Y4NA5ONHMHA5BLSRSVQTANCNFSM4UCACK7A
.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/lmgraves/AmnesiacML/issues/1#issuecomment-733724290, or unsubscribe https://github.com/notifications/unsubscribe-auth/AE4XIOKBPLDRE6CN5BYANELSRUE4XANCNFSM4UCACK7A .
Hi, I've updated the evaluation notebook as well as added a new notebook that tests the naive retraining, unlearning, and amnesiac unlearning methods on resnet18 and CIFAR100. Please let me know if you are having trouble testing it. Thanks! -Laura Graves
On Wed, Nov 25, 2020 at 10:08 PM Brown Chen notifications@github.com wrote:
Thank you for your reply! I do have some problems with the implementation of trainloder and testloader. Could you please publish the entire code or just send it to my email < brownchen7s@gmail.com> ?
Thanks a lot!
Laura Graves notifications@github.com 于2020年11月25日周三 下午10:01写道:
Hi! Thanks for reaching out. The sensitive data can be selected any way you choose - for the CIFAR and MNIST domains I selected an entire class and then had two test dataloaders, one including the sensitive class test data and one including the rest of the test data. To test the membership inference attack success I used a small random selection of training instances as sensitive data.
The Amnesiac ML Evaluation.ipynb file is the testing that we did for figure 7 in the paper, but looking at it right now it's a big buggy. I'll fix it later today and let you know when it's updated.
Thanks!
-Laura Graves
The github isn't the entire code base that we used, I hadn't included a full testing and training cycle
On Wed, Nov 25, 2020 at 2:17 AM Brown Chen notifications@github.com wrote:
Thank you for publishing the code. It's a great attempt for machine unlearning. By the way, how do you select the sensitive data during the unlearning process and I can't find the corresponding code in 'Amnesiac ML Evaluation.ipynb'. I want to reproduce the model accuracy on the target and non-target data. Looking forward to your reply!
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/lmgraves/AmnesiacML/issues/1, or unsubscribe <
https://github.com/notifications/unsubscribe-auth/AH2MZMUF5Y4NA5ONHMHA5BLSRSVQTANCNFSM4UCACK7A
.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <https://github.com/lmgraves/AmnesiacML/issues/1#issuecomment-733724290 , or unsubscribe < https://github.com/notifications/unsubscribe-auth/AE4XIOKBPLDRE6CN5BYANELSRUE4XANCNFSM4UCACK7A
.
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/lmgraves/AmnesiacML/issues/1#issuecomment-734046905, or unsubscribe https://github.com/notifications/unsubscribe-auth/AH2MZMS4QHAG74YZMYYX7ILSRXBDHANCNFSM4UCACK7A .
Thank you so much!
On Thu, Nov 26, 2020 at 11:11 PM Laura Graves notifications@github.com wrote:
Hi, I've updated the evaluation notebook as well as added a new notebook that tests the naive retraining, unlearning, and amnesiac unlearning methods on resnet18 and CIFAR100. Please let me know if you are having trouble testing it. Thanks! -Laura Graves
On Wed, Nov 25, 2020 at 10:08 PM Brown Chen notifications@github.com wrote:
Thank you for your reply! I do have some problems with the implementation of trainloder and testloader. Could you please publish the entire code or just send it to my email < brownchen7s@gmail.com> ?
Thanks a lot!
Laura Graves notifications@github.com 于2020年11月25日周三 下午10:01写道:
Hi! Thanks for reaching out. The sensitive data can be selected any way you choose - for the CIFAR and MNIST domains I selected an entire class and then had two test dataloaders, one including the sensitive class test data and one including the rest of the test data. To test the membership inference attack success I used a small random selection of training instances as sensitive data.
The Amnesiac ML Evaluation.ipynb file is the testing that we did for figure 7 in the paper, but looking at it right now it's a big buggy. I'll fix it later today and let you know when it's updated.
Thanks!
-Laura Graves
The github isn't the entire code base that we used, I hadn't included a full testing and training cycle
On Wed, Nov 25, 2020 at 2:17 AM Brown Chen notifications@github.com wrote:
Thank you for publishing the code. It's a great attempt for machine unlearning. By the way, how do you select the sensitive data during the unlearning process and I can't find the corresponding code in 'Amnesiac ML Evaluation.ipynb'. I want to reproduce the model accuracy on the target and non-target data. Looking forward to your reply!
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/lmgraves/AmnesiacML/issues/1, or unsubscribe <
https://github.com/notifications/unsubscribe-auth/AH2MZMUF5Y4NA5ONHMHA5BLSRSVQTANCNFSM4UCACK7A
.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub < https://github.com/lmgraves/AmnesiacML/issues/1#issuecomment-733724290 , or unsubscribe <
https://github.com/notifications/unsubscribe-auth/AE4XIOKBPLDRE6CN5BYANELSRUE4XANCNFSM4UCACK7A
.
— You are receiving this because you commented. Reply to this email directly, view it on GitHub <https://github.com/lmgraves/AmnesiacML/issues/1#issuecomment-734046905 , or unsubscribe < https://github.com/notifications/unsubscribe-auth/AH2MZMS4QHAG74YZMYYX7ILSRXBDHANCNFSM4UCACK7A
.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/lmgraves/AmnesiacML/issues/1#issuecomment-734351287, or unsubscribe https://github.com/notifications/unsubscribe-auth/AE4XIONT4NT6QULAAJ2Z233SRZV35ANCNFSM4UCACK7A .
What is the testtargetmodel in r, m = testtargetmodel()?
I can't find the corresponding definition.
Is this the complete code?
Thank you for publishing the code. It's a great attempt for machine unlearning. By the way, how do you select the sensitive data during the unlearning process and I can't find the corresponding code in 'Amnesiac ML Evaluation.ipynb'. I want to reproduce the model accuracy on the target and non-target data. Looking forward to your reply!