Zero-Knowledge Proofs from Learning Parity with Noise: Optimization, Verification, and Application - INRIA - Institut National de Recherche en Informatique et en Automatique
Communication Dans Un Congrès Année : 2025

Zero-Knowledge Proofs from Learning Parity with Noise: Optimization, Verification, and Application

Résumé

Zero-Knowledge Proofs (ZKPs) are cryptographic building blocks of many privacy-preserving security protocols. An important research focus in this area is the development of post-quantum ZKPs. These are ZKPs whose security is reduced to computational hardness assumptions that are assumed to be intractable even by scalable quantum computers.

In this paper, we study the post-quantum ZKPs of Jain, Krenn, Pietrzak, and Tentes (Asiacrypt 2012). These are the only ZKPs for proving arbitrary binary statements whose security reduces to the Learning Parity with Noise (LPN) problem-a very conservative post-quantum hardness assumption.

We make the following contributions to further develop the potential and understanding of these ZKPs. First, we optimize the efficiency of the verifier by several orders of magnitude, making this part as computationally light as that of the prover. Second, we show that the only open source implementation of these ZKPs does not implement them correctly, allowing a malicious prover to convince the verifier of false statements. Third, we formally verify for the first time the security of these (optimized) ZKPs in EasyCrypt. Fourth, we show how these ZKPs can be used to construct the first code-based ZKP of shuffle and verifiable e-voting protocol.

Fichier principal
Vignette du fichier
Zero_Knowledge_Proofs_from_Learning_Parity_with_Noise__Optimization__Verification__and_Application.pdf (377.74 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04856221 , version 1 (26-12-2024)

Licence

Identifiants

  • HAL Id : hal-04856221 , version 1

Citer

Thomas Haines, Rafieh Mosaheb, Johannes Müller, Reetika Reetika. Zero-Knowledge Proofs from Learning Parity with Noise: Optimization, Verification, and Application. IEEE Computer Security Foundations (CSF) Symposium 2025, Jun 2025, Santa Cruz, United States. ⟨hal-04856221⟩
0 Consultations
0 Téléchargements

Partager

More