Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

A Survey on Verifiable Cross-Silo Federated Learning

Authors: Aleksei Korneev, Jan Ramon

TMLR 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we present a survey on verifiable cross-silo FL. We analyze various protocols, fit them in a taxonomy, and compare their efficiency and threat models. We also analyze Zero-Knowledge Proof (ZKP) schemes and discuss how their overall cost in a FL context can be minimized. Lastly, we identify research gaps and discuss potential directions for future scientific work.
Researcher Affiliation Academia Aleksei Korneev EMAIL University of Lille, Inria, CNRS, Centrale Lille, UMR 9189 CRISt AL Jan Ramon EMAIL University of Lille, Inria, CNRS, Centrale Lille, UMR 9189 CRISt AL
Pseudocode Yes Algorithm 1 Generic RA-based verification For a client Ci : Input: Private data di 1. Receive the global model θ from the server 2. Compute the local model θi using di and θ 3. Compute the ciphertext/tag ti using di and/or θi 4. Send θi and ti to the server 5. Receive the updated global model θ+ and the aggregated ciphertext/tag t from the server 6. Verify the correctness of θ+ using t For a server S : Input: Global model θ 1. Send the global model θ to each client 2. Receive ciphertexts/tags {ti}C i=1 and local models {θi}C i=1 from all clients 3. Compute the updated global model θ+ by aggregating {θi}C i=1 4. Compute the aggregated ciphertext/tag t by aggregating {ti}C i=1 5. Send θ+ and t to all clients
Open Source Code No The paper is a survey and analysis of existing verifiable cross-silo FL protocols and ZKP schemes. It does not describe a new methodology that would typically have accompanying source code. No explicit statement or link to source code is provided for the work presented in this paper.
Open Datasets No The paper is a survey and analysis of existing verifiable cross-silo FL protocols. It does not conduct its own experiments or use any specific dataset for evaluation within this paper.
Dataset Splits No The paper is a survey and analysis of existing verifiable cross-silo FL protocols. It does not conduct its own experiments or specify dataset splits.
Hardware Specification No The paper is a survey and analysis of existing verifiable cross-silo FL protocols. It does not conduct its own experiments and therefore does not specify any hardware for running them.
Software Dependencies No The paper is a survey and analysis of existing verifiable cross-silo FL protocols. It does not describe an implementation of its own methodology that would require software dependencies.
Experiment Setup No The paper is a survey and analysis of existing verifiable cross-silo FL protocols. It does not conduct its own experiments or provide details on an experimental setup.