Although federated learning offers a level of privacy by aggregating user data without direct
access, it remains inherently vulnerable to various attacks, including poisoning attacks …

This paper introduces Flamingo, a system for secure aggregation of data across a large set
of clients. In secure aggregation, a server sums up the private inputs of clients and obtains …

The modern Internet is built on systems that incentivize collection of information about users.
In order to minimize privacy loss, it is desirable to prevent these systems from collecting …

This paper introduces LERNA, a new framework for single-server secure aggregation. Our
protocols are tailored to the setting where multiple consecutive aggregation phases are …

Zero-knowledge range proofs (ZKRPs) allow a prover to convince a verifier that a secret
value lies in a given interval. ZKRPs have numerous applications: from anonymous …

Federated learning (FL) has become a popular mode of learning, allowing model training
without the need to share data. Unfortunately, it remains vulnerable to privacy leakage and …

In this work, we introduce a lightweight secure aggregation protocol that guarantees
liveness (ie, guaranteed output delivery), robust against faulty inputs and security against …

Homomorphic Encryption (HE) facilitates the preservation of privacy in federated learning
(FL) aggregation. However, HE imposes significant computational and communication …

The shuffle model has recently emerged as a popular setting for differential privacy, where
clients can communicate with a central server using anonymous channels or an …

Federated Learning (FL) enables multiple clients to collaboratively train a model without
sharing their private data. However, the deployment of FL in real-world applications is …