Secure Federated Correlation Test and Entropy Estimation

Qi Pang, Lun Wang, Shuai Wang, Wenting Zheng, Dawn Song
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26990-27010, 2023.

Abstract

We propose the first federated correlation test framework compatible with secure aggregation, namely FED-$\chi^2$. In our protocol, the statistical computations are recast as frequency moment estimation problems, where the clients collaboratively generate a shared projection matrix and then use stable projection to encode the local information in a compact vector. As such encodings can be linearly aggregated, secure aggregation can be applied to conceal the individual updates. We formally establish the security guarantee of FED-$\chi^2$ by proving that only the minimum necessary information (i.e., the correlation statistics) is revealed to the server. We show that our protocol can be naturally extended to estimate other statistics that can be recast as frequency moment estimations. By accommodating Shannon’e Entropy in FED-$\chi^2$, we further propose the first secure federated entropy estimation protocol, FED-$H$. The evaluation results demonstrate that FED-$\chi^2$ and FED-$H$ achieve good performance with small client-side computation overhead in several real-world case studies.

Cite this Paper


BibTeX
@InProceedings{pmlr-v202-pang23a, title = {Secure Federated Correlation Test and Entropy Estimation}, author = {Pang, Qi and Wang, Lun and Wang, Shuai and Zheng, Wenting and Song, Dawn}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {26990--27010}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/pang23a/pang23a.pdf}, url = {https://proceedings.mlr.press/v202/pang23a.html}, abstract = {We propose the first federated correlation test framework compatible with secure aggregation, namely FED-$\chi^2$. In our protocol, the statistical computations are recast as frequency moment estimation problems, where the clients collaboratively generate a shared projection matrix and then use stable projection to encode the local information in a compact vector. As such encodings can be linearly aggregated, secure aggregation can be applied to conceal the individual updates. We formally establish the security guarantee of FED-$\chi^2$ by proving that only the minimum necessary information (i.e., the correlation statistics) is revealed to the server. We show that our protocol can be naturally extended to estimate other statistics that can be recast as frequency moment estimations. By accommodating Shannon’e Entropy in FED-$\chi^2$, we further propose the first secure federated entropy estimation protocol, FED-$H$. The evaluation results demonstrate that FED-$\chi^2$ and FED-$H$ achieve good performance with small client-side computation overhead in several real-world case studies.} }
Endnote
%0 Conference Paper %T Secure Federated Correlation Test and Entropy Estimation %A Qi Pang %A Lun Wang %A Shuai Wang %A Wenting Zheng %A Dawn Song %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-pang23a %I PMLR %P 26990--27010 %U https://proceedings.mlr.press/v202/pang23a.html %V 202 %X We propose the first federated correlation test framework compatible with secure aggregation, namely FED-$\chi^2$. In our protocol, the statistical computations are recast as frequency moment estimation problems, where the clients collaboratively generate a shared projection matrix and then use stable projection to encode the local information in a compact vector. As such encodings can be linearly aggregated, secure aggregation can be applied to conceal the individual updates. We formally establish the security guarantee of FED-$\chi^2$ by proving that only the minimum necessary information (i.e., the correlation statistics) is revealed to the server. We show that our protocol can be naturally extended to estimate other statistics that can be recast as frequency moment estimations. By accommodating Shannon’e Entropy in FED-$\chi^2$, we further propose the first secure federated entropy estimation protocol, FED-$H$. The evaluation results demonstrate that FED-$\chi^2$ and FED-$H$ achieve good performance with small client-side computation overhead in several real-world case studies.
APA
Pang, Q., Wang, L., Wang, S., Zheng, W. & Song, D.. (2023). Secure Federated Correlation Test and Entropy Estimation. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:26990-27010 Available from https://proceedings.mlr.press/v202/pang23a.html.

Related Material