ACORN: Input Validation for Secure Aggregation


James Bell and Adrià Gascón, Google LLC; Tancrède Lepoint, Amazon; Baiyu Li, Sarah Meiklejohn, and Mariana Raykova, Google LLC; Cathie Yun


Secure aggregation enables a server to learn the sum of client-held vectors in a privacy-preserving way, and has been applied to distributed statistical analysis and machine learning. In this paper, we both introduce a more efficient secure aggregation protocol and extend secure aggregation by enabling input validation, in which the server can check that clients' inputs satisfy constraints such as L0, L2, and Linfinity bounds. This prevents malicious clients from gaining disproportionate influence on the aggregate statistics or machine learning model. Our new secure aggregation protocol improves the computational efficiency of the state-of-the-art protocol of Bell et al. (CCS 2020) both asymptotically and concretely: we show via experimental evaluation that it results in 2-8X speedups in client computation in practical scenarios. Likewise, our extended protocol with input validation improves on prior work by more than 30X in terms of client communication (with comparable computation costs). Compared to the base protocols without input validation, the extended protocols incur only 0.1X additional communication, and can process binary indicator vectors of length 1M, or 16-bit dense vectors of length 250K, in under 80s of computation per client.

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

@inproceedings {291112,
author = {James Bell and Adri{\`a} Gasc{\'o}n and Tancr{\`e}de Lepoint and Baiyu Li and Sarah Meiklejohn and Mariana Raykova and Cathie Yun},
title = {{ACORN}: Input Validation for Secure Aggregation},
booktitle = {32nd USENIX Security Symposium (USENIX Security 23)},
year = {2023},
isbn = {978-1-939133-37-3},
address = {Anaheim, CA},
pages = {4805--4822},
url = {},
publisher = {USENIX Association},
month = aug

Presentation Video