An implementation of Secure Aggregation algorithm based on "Practical Secure Aggregation for Privacy-Preserving Machine Learning (Bonawitz et. al)" in Python.
81
stars
20
forks
source link
Inquiry about the implementation of "Secure Single-Server Aggregation with (Poly)Logarithmic Overhead" paper #1
I hope this email finds you well. I came across your implementation of "Practical Secure Aggregation for Privacy-Preserving Machine Learning (Bonawitz et. al)" on GitHub and was quite impressed with your work. I appreciate your contributions in this field.
I am currently conducting research in the area of secure aggregation for privacy-preserving machine learning, and I recently came across another paper by Bonawitz et al. titled "Secure Single-Server Aggregation with (Poly)Logarithmic Overhead." I was wondering if you have also implemented this follow-up paper or if you have any knowledge of existing implementations.
If you have any information or resources related to the implementation of "Secure Single-Server Aggregation with (Poly)Logarithmic Overhead," I would be grateful if you could share them with me. Your expertise and insights would greatly benefit my research.
Thank you for your time and consideration. I look forward to hearing from you.
Dear Ammar Tahir:
I hope this email finds you well. I came across your implementation of "Practical Secure Aggregation for Privacy-Preserving Machine Learning (Bonawitz et. al)" on GitHub and was quite impressed with your work. I appreciate your contributions in this field.
I am currently conducting research in the area of secure aggregation for privacy-preserving machine learning, and I recently came across another paper by Bonawitz et al. titled "Secure Single-Server Aggregation with (Poly)Logarithmic Overhead." I was wondering if you have also implemented this follow-up paper or if you have any knowledge of existing implementations.
If you have any information or resources related to the implementation of "Secure Single-Server Aggregation with (Poly)Logarithmic Overhead," I would be grateful if you could share them with me. Your expertise and insights would greatly benefit my research.
Thank you for your time and consideration. I look forward to hearing from you.
Best regards