Related papers: Secure Aggregation with an Oblivious Server

Aggregation of values that need to be kept confidential while guaranteeing the robustness of the process and the correctness of the result is required in an increasing number of applications. We propose an aggregation algorithm, which…

Reducing the database space overhead is critical in big-data processing. In this paper, we revisit oblivious RAM (ORAM) using big-data standard for the database space overhead. ORAM is a cryptographic primitive that enables users to perform…

We propose SwiftAgg, a novel secure aggregation protocol for federated learning systems, where a central server aggregates local models of $N$ distributed users, each of size $L$, trained on their local data, in a privacy-preserving manner.…

A blind decryption scheme enables a user to query decryptions from a decryption server without revealing information about the plaintext message. Such schemes are useful, for example, for the implementation of privacy preserving encrypted…

Although one-time pad encrypted files can be sent through Internet channels, the need for renewing shared secret keys have made this method unpractical. This work presents a scheme to turn practical the fast sharing of random keys over…

Federated Learning (FL) enables multiple users to collaboratively train a machine learning model without sharing raw data, making it suitable for privacy-sensitive applications. However, local model or weight updates can still leak…

Federated Learning enables one to jointly train a machine learning model across distributed clients holding sensitive datasets. In real-world settings, this approach is hindered by expensive communication and privacy concerns. Both of these…

With gradient coding, a user node can efficiently aggregate gradients from server nodes processing local datasets, achieving low communication costs and maintaining resilience against straggling servers. This paper considers a secure…

The noisy-storage model of quantum cryptography allows for information-theoretically secure two-party computation based on the assumption that a cheating user has at most access to an imperfect, noisy quantum memory, whereas the honest…

In this paper, we study the fundamental limits of hierarchical secure aggregation under unreliable communication. We consider a hierarchical network where each client connects to multiple relays, and both client-to-relay and relay-to-server…

Secure aggregation is a popular protocol in privacy-preserving federated learning, which allows model aggregation without revealing the individual models in the clear. On the other hand, conventional secure aggregation protocols incur a…

This article bridges the gap between two topics used in sharing an encryption key: (i) Key Consolidation, i.e., extracting two identical strings of bits from two information sources with similarities (common randomness). (ii) Quantum-safe…

This paper considers a new secure gradient coding problem with uncoded groupwise keys, formalized as a (K, N, N_r, M, S) secure gradient coding model, where a user aims to compute the sum of the gradients from K datasets with the assistance…

We consider training models on private data that are distributed across user devices. To ensure privacy, we add on-device noise and use secure aggregation so that only the noisy sum is revealed to the server. We present a comprehensive…

We consider information theoretic secret key agreement and secure function computation by multiple parties observing correlated data, with access to an interactive public communication channel. Our main result is an upper bound on the…

It was shown in [WST08] that cryptographic primitives can be implemented based on the assumption that quantum storage of qubits is noisy. In this work we analyze a protocol for the universal task of oblivious transfer that can be…

Federated learning enables collaborative model training across distributed clients, yet vanilla FL exposes client updates to the central server. Secure-aggregation schemes protect privacy against an honest-but-curious server, but existing…

Secure linear aggregation is to linearly aggregate private inputs of different users with privacy protection. The server in a federated learning (FL) environment can fulfill any linear computation on private inputs of users through the…

Motivated by the importance of floating-point computations, we study the problem of securely and accurately summing many floating-point numbers. Prior work has focused on security absent accuracy or accuracy absent security, whereas our…

This work shows how a secure Internet can be implemented through a fast key distribution system that uses physical noise to protect the transmitted information. Starting from a shared random sequence $K_0$ between two (or more) users,…