Scalable zkSNARKs for Matrix Computations: A Generic Framework for Verifiable Deep Learning.
Published in The International Conference on the Theory and Application of Cryptology and Information Security 2025 (Asiacrypt 2025). December 8 - 12, 2025, Melbourne, Australia, 2025
Overview
A generic zkSNARK framework for scalable verification of matrix computations, with applications to verifiable deep-learning workloads.
Cite
Mingshu Cong, Sherman S. M. Chow, Siu Ming Yiu, and Tsz Hon Yuen. “Scalable zkSNARKs for Matrix Computations: A Generic Framework for Verifiable Deep Learning.” In Advances in Cryptology – ASIACRYPT 2025, Lecture Notes in Computer Science, vol. 16249, pp. 363–395, 2026.