# ZKP-FedEval: Verifiable and Privacy-Preserving Federated Evaluation using Zero-Knowledge Proofs

arXiv: https://arxiv.org/abs/2507.11649 · HTML: https://mlsanity.com/paper/2507.11649/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 15 Jul 2025.

## Builds on (most cited first, 8 of 8)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [Exploiting Unintended Feature Leakage in Collaborative Learning](https://mlsanity.com/paper/1805.04049/) (2018)
- [Gazelle: A Low Latency Framework for Secure Neural Network Inference](https://mlsanity.com/paper/1801.05507/) (2018)
- [Securing Health Data on the Blockchain: A Differential Privacy and Federated Learning Framework](https://mlsanity.com/paper/2405.11580/) (2024)
- [Securing Blockchain-based IoT Systems with Physical Unclonable Functions and Zero-Knowledge Proofs](https://mlsanity.com/paper/2405.12322/) (2024)

## Built on by (most cited first, 1 of 1)

- [FedSkipTwin: Digital-Twin-Guided Client Skipping for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2507.13624/) (2025)

## Abstract (arXiv)

Federated Learning (FL) enables collaborative model training on decentralized data without exposing raw data. However, the evaluation phase in FL may leak sensitive information through shared performance metrics. In this paper, we propose a novel protocol that incorporates Zero-Knowledge Proofs (ZKPs) to enable privacy-preserving and verifiable evaluation for FL. Instead of revealing raw loss values, clients generate a succinct proof asserting that their local loss is below a predefined threshold. Our approach is implemented without reliance on external APIs, using self-contained modules for federated learning simulation, ZKP circuit design, and experimental evaluation on both the MNIST and Human Activity Recognition (HAR) datasets. We focus on a threshold-based proof for a simple Convolutional Neural Network (CNN) model (for MNIST) and a multi-layer perceptron (MLP) model (for HAR), and evaluate the approach in terms of computational overhead, communication cost, and verifiability.