Bionetta: Efficient Client-Side Zero-Knowledge Machine Learning Proving

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zakharov, Dmytro, Kurbatov, Oleksandr, Sdobnov, Artem, Soukhanov, Lev, Sekhin, Yevhenii, Volovyk, Vitalii, Velykodnyi, Mykhailo, Cherepovskyi, Mark, Baibula, Kyrylo, Antadze, Lasha, Kravchenko, Pavlo, Dubinin, Volodymyr, Panasenko, Yaroslav
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917132741115904
author Zakharov, Dmytro
Kurbatov, Oleksandr
Sdobnov, Artem
Soukhanov, Lev
Sekhin, Yevhenii
Volovyk, Vitalii
Velykodnyi, Mykhailo
Cherepovskyi, Mark
Baibula, Kyrylo
Antadze, Lasha
Kravchenko, Pavlo
Dubinin, Volodymyr
Panasenko, Yaroslav
author_facet Zakharov, Dmytro
Kurbatov, Oleksandr
Sdobnov, Artem
Soukhanov, Lev
Sekhin, Yevhenii
Volovyk, Vitalii
Velykodnyi, Mykhailo
Cherepovskyi, Mark
Baibula, Kyrylo
Antadze, Lasha
Kravchenko, Pavlo
Dubinin, Volodymyr
Panasenko, Yaroslav
contents In this report, we compare the performance of our UltraGroth-based zero-knowledge machine learning framework Bionetta to other tools of similar purpose such as EZKL, Lagrange's deep-prove, or zkml. The results show a significant boost in the proving time for custom-crafted neural networks: they can be proven even on mobile devices, enabling numerous client-side proving applications. While our scheme increases the cost of one-time preprocessing steps, such as circuit compilation and generating trusted setup, our approach is, to the best of our knowledge, the only one that is deployable on the native EVM smart contracts without overwhelming proof size and verification overheads.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06784
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bionetta: Efficient Client-Side Zero-Knowledge Machine Learning Proving
Zakharov, Dmytro
Kurbatov, Oleksandr
Sdobnov, Artem
Soukhanov, Lev
Sekhin, Yevhenii
Volovyk, Vitalii
Velykodnyi, Mykhailo
Cherepovskyi, Mark
Baibula, Kyrylo
Antadze, Lasha
Kravchenko, Pavlo
Dubinin, Volodymyr
Panasenko, Yaroslav
Cryptography and Security
Computer Vision and Pattern Recognition
In this report, we compare the performance of our UltraGroth-based zero-knowledge machine learning framework Bionetta to other tools of similar purpose such as EZKL, Lagrange's deep-prove, or zkml. The results show a significant boost in the proving time for custom-crafted neural networks: they can be proven even on mobile devices, enabling numerous client-side proving applications. While our scheme increases the cost of one-time preprocessing steps, such as circuit compilation and generating trusted setup, our approach is, to the best of our knowledge, the only one that is deployable on the native EVM smart contracts without overwhelming proof size and verification overheads.
title Bionetta: Efficient Client-Side Zero-Knowledge Machine Learning Proving
topic Cryptography and Security
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.06784