REVIEW 3 cited by
Scalable and Differentially Private Distributed Aggregation in the Shuffled Model
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Federated learning promises to make machine learning feasible on distributed, private datasets by implementing gradient descent using secure aggregation methods. The idea is to compute a global weight update without revealing the contributions of individual users. Current practical protocols for secure aggregation work in an "honest but curious" setting where a curious adversary observing all communication to and from the server cannot learn any private information assuming the server is honest and follows the protocol. A more scalable and robust primitive for privacy-preserving protocols is shuffling of user data, so as to hide the origin of each data item. Highly scalable and secure protocols for shuffling, so-called mixnets, have been proposed as a primitive for privacy-preserving analytics in the Encode-Shuffle-Analyze framework by Bittau et al., which was later analytically studied by Erlingsson et al. and Cheu et al.. The recent papers by Cheu et al., and Balle et al. have given protocols for secure aggregation that achieve differential privacy guarantees in this "shuffled model". Their protocols come at a cost, though: Either the expected aggregation error or the amount of communication per user scales as a polynomial $n^{\Omega(1)}$ in the number of users $n$. In this paper we propose simple and more efficient protocol for aggregation in the shuffled model, where communication as well as error increases only polylogarithmically in $n$. Our new technique is a conceptual "invisibility cloak" that makes users' data almost indistinguishable from random noise while introducing zero distortion on the sum.
Forward citations
Cited by 3 Pith papers
-
On the Power of Multiple Anonymous Messages
Single-message shuffled-model frequency estimation has optimal error about min(n^{1/4}, sqrt(B)); multi-message protocols achieve polylogarithmic error with polylogarithmic communication.
-
Improving Utility and Security of the Shuffler-based Differential Privacy
Local hashing with an optimized output size and a new encrypted oblivious-shuffle protocol improve utility and attack-resistance in shuffler-based differential privacy.
-
Federated Learning: Challenges, Methods, and Future Directions
This survey maps federated learning's core challenges, reviews existing methods, and lists open problems.
Discussion (0). Continue with ORCID to comment.