We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
在阅读您A Probabilistic Fluctuation based Membership Inference Attack文章和代码的时候有几点不明确的地方: 1)文中的eq(12)是什么意思,我看您用monte carlo来解释,但是在代码里无论是ddpm_loss还是ddim_loss都没有关于monte carlo的部分; 2)为什么在代码实现了,ddpm_loss直接使用diffusion的loss,而ddim_loss则要先一步步的inversion到t步作为target,再inversion一步然后在reverse作为predict呢?他们俩的差别是什么,为什么这么做?ddim_loss不能直接用diffusion loss吗?这里是为了减少不确定性? 3)为什么文中提到了shadow model,但是代码里却没有用到; 4)reference model的意义是什么,文中感觉没有解释的很清楚,不加reference model会没有效果吗?
The text was updated successfully, but these errors were encountered:
期待您的回复
Sorry, something went wrong.
No branches or pull requests
在阅读您A Probabilistic Fluctuation based Membership Inference Attack文章和代码的时候有几点不明确的地方:
1)文中的eq(12)是什么意思,我看您用monte carlo来解释,但是在代码里无论是ddpm_loss还是ddim_loss都没有关于monte carlo的部分;
2)为什么在代码实现了,ddpm_loss直接使用diffusion的loss,而ddim_loss则要先一步步的inversion到t步作为target,再inversion一步然后在reverse作为predict呢?他们俩的差别是什么,为什么这么做?ddim_loss不能直接用diffusion loss吗?这里是为了减少不确定性?
3)为什么文中提到了shadow model,但是代码里却没有用到;
4)reference model的意义是什么,文中感觉没有解释的很清楚,不加reference model会没有效果吗?
The text was updated successfully, but these errors were encountered: