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
希望调用同态加密之类的密码学算法实现梯度加密,在这个框架的那部分进行修改能够实现?
The text was updated successfully, but these errors were encountered:
你好,需要修改Client.initialize初始化密钥,修改Client.pack加密上传的内容,修改Server.iterate处理接收到的内容的方式
Sorry, something went wrong.
好的 谢谢
希望调用同态加密之类的密码学算法实现梯度加密,在这个框架的那部分进行修改能够实现? 你好,需要修改Client.initialize初始化密钥,修改Client.pack加密上传的内容,修改Server.iterate处理接收到的内容的方式
您好 目前我存在一个疑惑就是对于梯度进行加密,但是如何获得您项目中训练模型的梯度,我发现您在对于梯度进行加减主要是使用fmodle中的函数,但是我直接输出梯度是一个tensor([[-1.1742e-06, -6.4992e-06, -6.2563e-05, ..., -5.5793e-05, 9.1988e-06, 1.5008e-05], [ 9.4393e-05, -6.7191e-05, 9.7635e-05, ..., -1.2369e-03, -5.2005e-04, -3.3128e-05], [ 0.0000e+00, 0.0000e+00, 0.0000e+00, ..., 0.0000e+00, 0.0000e+00, 0.0000e+00], 类似这样的数据,可能我有点表述不清,就是是可以直接在这样的数据上进行计算吗?因为我想要实现加密,就需要对具体数据进行操作,但是对于您的实现方式仍有困惑。然后我看到的现有的开源代码关于加密,是将模型训练的过程变成数学计算方式,所以我在此之间存在困惑
No branches or pull requests
希望调用同态加密之类的密码学算法实现梯度加密,在这个框架的那部分进行修改能够实现?
The text was updated successfully, but these errors were encountered: