Abdolmaleki, B., Asadi, A.R., Asadi, V.R. et al. (4 more authors) (2026) VeriDP: Verifiable Differentially Private Training. In: Proceedings on Privacy Enhancing Technologies. Privacy Enhancing Technologies Symposium (PoPETs), 20-25 Jul 2026, Calgary, Alberta, Canada. Vol. 2026 (3). Privacy Enhancing Technologies Symposium Advisory Board, pp. 48-64. ISSN: 2299-0984. EISSN: 2299-0984.
Abstract
Stochastic Gradient Descent (SGD) is the foundation of modern machine learning (ML). In privacy-sensitive settings, gradients can reveal details about individual data points. Differential Privacy (DP) protects sensitive data during ML training by clipping gradients and adding calibrated Gaussian noise. However, existing frameworks assume semi-honest participants, which fails in adversarial or federated environments where malicious actors can bypass or alter the noise addition process, breaking privacy guarantees. We present VeriDP, a framework for verifiable differentially private training that cryptographically enforces and proves the correct execution of differentially private stochastic gradient descent (DP-SGD) in zero knowledge. VeriDP integrates Zero-Knowledge Proofs (ZKPs) with polynomial commitments, sumcheck and GKR-based proofs, and incrementally verifiable computation (IVC) to generate compact proofs of correct gradient computation, clipping, averaging, and Gaussian noise generation—without revealing private data or randomness. Unlike previous systems that only verify the final privacy budget, VeriDP enables per-iteration verifiability of each model update, providing strong privacy assurances even in adversarial settings. This establishes a novel and complete Zero-Knowledge Proof of Differentially Private Stochastic Gradient Descent (ZK-DPSGD), uniting differential privacy and verifiable computation for secure and auditable ML. Our evaluation shows that prover time increases linearly with the number of input samples, while both verifier time (2–5 ms) and proof size (3–4 KB) remain compact and effectively constant.
Metadata
| Item Type: | Proceedings Paper |
|---|---|
| Authors/Creators: |
|
| Copyright, Publisher and Additional Information: | © 2026 Copyright held by the owner/author(s). This work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this license visit https://creativecommons.org/licenses/by/4.0/ |
| Keywords: | Zero-Knowledge Proof; Differential Privacy; Verifiable Machine Learning; Stochastic Gradient Descent |
| Dates: |
|
| Institution: | The University of Sheffield |
| Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
| Date Deposited: | 27 Oct 2026 11:38 |
| Last Modified: | 27 Oct 2026 11:40 |
| Status: | Published |
| Publisher: | Privacy Enhancing Technologies Symposium Advisory Board |
| Refereed: | Yes |
| Identification Number: | 10.56553/popets-2026-0070 |
| Related URLs: | |
| Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:247156 |
Download
Filename: popets-2026-0070.pdf
Licence: CC-BY 4.0
CORE (COnnecting REpositories)
CORE (COnnecting REpositories)