Samplable Anonymous Aggregation for Private Federated Data Analysis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929426741067776 |
|---|---|
| author | Talwar, Kunal Wang, Shan McMillan, Audra Jina, Vojta Feldman, Vitaly Bansal, Pansy Basile, Bailey Cahill, Aine Chan, Yi Sheng Chatzidakis, Mike Chen, Junye Chick, Oliver Chitnis, Mona Ganta, Suman Goren, Yusuf Granqvist, Filip Guo, Kristine Jacobs, Frederic Javidbakht, Omid Liu, Albert Low, Richard Mascenik, Dan Myers, Steve Park, David Park, Wonhee Parsa, Gianni Pauly, Tommy Priebe, Christian Rishi, Rehan Rothblum, Guy Scaria, Michael Song, Linmao Song, Congzheng Tarbe, Karl Vogt, Sebastian Winstrom, Luke Zhou, Shundong |
| author_facet | Talwar, Kunal Wang, Shan McMillan, Audra Jina, Vojta Feldman, Vitaly Bansal, Pansy Basile, Bailey Cahill, Aine Chan, Yi Sheng Chatzidakis, Mike Chen, Junye Chick, Oliver Chitnis, Mona Ganta, Suman Goren, Yusuf Granqvist, Filip Guo, Kristine Jacobs, Frederic Javidbakht, Omid Liu, Albert Low, Richard Mascenik, Dan Myers, Steve Park, David Park, Wonhee Parsa, Gianni Pauly, Tommy Priebe, Christian Rishi, Rehan Rothblum, Guy Scaria, Michael Song, Linmao Song, Congzheng Tarbe, Karl Vogt, Sebastian Winstrom, Luke Zhou, Shundong |
| contents | We revisit the problem of designing scalable protocols for private statistics and private federated learning when each device holds its private data. Locally differentially private algorithms require little trust but are (provably) limited in their utility. Centrally differentially private algorithms can allow significantly better utility but require a trusted curator. This gap has led to significant interest in the design and implementation of simple cryptographic primitives, that can allow central-like utility guarantees without having to trust a central server.
Our first contribution is to propose a new primitive that allows for efficient implementation of several commonly used algorithms, and allows for privacy accounting that is close to that in the central setting without requiring the strong trust assumptions it entails. {\em Shuffling} and {\em aggregation} primitives that have been proposed in earlier works enable this for some algorithms, but have significant limitations as primitives. We propose a {\em Samplable Anonymous Aggregation} primitive, which computes an aggregate over a random subset of the inputs and show that it leads to better privacy-utility trade-offs for various fundamental tasks. Secondly, we propose a system architecture that implements this primitive and perform a security analysis of the proposed system. Our design combines additive secret-sharing with anonymization and authentication infrastructures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_15017 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Samplable Anonymous Aggregation for Private Federated Data Analysis Talwar, Kunal Wang, Shan McMillan, Audra Jina, Vojta Feldman, Vitaly Bansal, Pansy Basile, Bailey Cahill, Aine Chan, Yi Sheng Chatzidakis, Mike Chen, Junye Chick, Oliver Chitnis, Mona Ganta, Suman Goren, Yusuf Granqvist, Filip Guo, Kristine Jacobs, Frederic Javidbakht, Omid Liu, Albert Low, Richard Mascenik, Dan Myers, Steve Park, David Park, Wonhee Parsa, Gianni Pauly, Tommy Priebe, Christian Rishi, Rehan Rothblum, Guy Scaria, Michael Song, Linmao Song, Congzheng Tarbe, Karl Vogt, Sebastian Winstrom, Luke Zhou, Shundong Cryptography and Security Machine Learning We revisit the problem of designing scalable protocols for private statistics and private federated learning when each device holds its private data. Locally differentially private algorithms require little trust but are (provably) limited in their utility. Centrally differentially private algorithms can allow significantly better utility but require a trusted curator. This gap has led to significant interest in the design and implementation of simple cryptographic primitives, that can allow central-like utility guarantees without having to trust a central server. Our first contribution is to propose a new primitive that allows for efficient implementation of several commonly used algorithms, and allows for privacy accounting that is close to that in the central setting without requiring the strong trust assumptions it entails. {\em Shuffling} and {\em aggregation} primitives that have been proposed in earlier works enable this for some algorithms, but have significant limitations as primitives. We propose a {\em Samplable Anonymous Aggregation} primitive, which computes an aggregate over a random subset of the inputs and show that it leads to better privacy-utility trade-offs for various fundamental tasks. Secondly, we propose a system architecture that implements this primitive and perform a security analysis of the proposed system. Our design combines additive secret-sharing with anonymization and authentication infrastructures. |
| title | Samplable Anonymous Aggregation for Private Federated Data Analysis |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2307.15017 |