Fetching the paper…
Reading the bibliography…
Ensuring that AI models are both verifiable and privacy-preserving is important for trust, accountability, and compliance.
A probabilistic remark on algebraic program testing
Richard A Demillo and Richard J Lipton · 1978
Earlier work this paper cites.
Constant-size commitments to polynomials and their applications
Aniket Kate, Gregory M Zaverucha, and Ian Goldberg · 2010
Earlier work this paper cites.
Very deep convolutional networks for large-scale image recognition
Karen Simonyan and Andrew Zisserman · 2014
Earlier work this paper cites.
Geppetto: Versatile verifiable computation
Craig Costello, Cedric Fournet, Jon Howell, Markulf Kohlweiss, Benjamin Kreuter, Michael Naehrig, Bryan Parno, and Samee Zahur · 2015
Earlier work this paper cites.
On the size of pairing-based non-interactive arguments
Jens Groth · 2016
Earlier work this paper cites.
Identity mappings in deep residual networks
Kaiming He, X. Zhang, Shaoqing Ren, and Jian Sun · 2016
Earlier work this paper cites.
Prover-efficient commit-and-prove zero-knowledge SNARKs
Helger Lipmaa · 2016
Earlier work this paper cites.
Preparing for the future of artificial intelligence, October 2016
National Science and Technology Council Committee on Technology · 2016
Earlier work this paper cites.
Bulletproofs: Short proofs for confidential transactions and more
Benedikt Bünz, Jonathan Bootle, Dan Boneh, Andrew Poelstra, Pieter Wuille, and Greg Maxwell · 2018
Earlier work this paper cites.
The minimal neural network that achieves 99% on mnist
Ruslan Grimov · 2018
Earlier work this paper cites.
Blind justice: Fairness with encrypted sensitive attributes
Niki Kilbertus, Adrià Gascón, Matt J Kusner, Michael Veale, Krishna P Gummadi, and Adrian Weller · 2018
Earlier work this paper cites.
Mobilenetv2: Inverted residuals and linear bottlenecks
Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen · 2018
Earlier work this paper cites.
Halo: Recursive proof composition without a trusted setup
Sean Bowe, Jack Grigg, and Daira Hopwood · 2019
Earlier work this paper cites.
LegoSNARK: Modular design and composition of succinct zero-knowledge proofs
Matteo Campanelli, Dario Fiore, and Anaïs Querol · 2019
Earlier work this paper cites.
Plonk: Permutations over lagrange-bases for oecumenical noninteractive arguments of knowledge
Ariel Gabizon, Zachary J Williamson, and Oana Ciobotaru · 2019
Earlier work this paper cites.
Deep learning recommendation model for personalization and recommendation systems
Maxim Naumov, Dheevatsa Mudigere, Hao-Jun Michael Shi, et al · 2019
Earlier work this paper cites.
Language models are unsupervised multitask learners
Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever · 2019
Earlier work this paper cites.
Can you trust this prediction? auditing pointwise reliability after learning
Peter Schulam and Suchi Saria · 2019
Earlier work this paper cites.
Lunar: a toolbox for more efficient universal and updatable zkSNARKs and commit-and-prove extensions
Matteo Campanelli, Antonio Faonio, Dario Fiore, Anaïs Querol, and Hadrián Rodríguez · 2020
Earlier work this paper cites.
Marlin: Preprocessing zkSNARKs with universal and updatable SRS
Alessandro Chiesa, Yuncong Hu, Mary Maller, Pratyush Mishra, Noah Vesely, and Nicholas Ward · 2020
Cited alongside, same era.
vCNN: Verifiable convolutional neural network based on zk-SNARKs
Seunghwa Lee, Hankyung Ko, Jihye Kim, and Hyunok Oh · 2020
Cited alongside, same era.
Fairness in the eyes of the data: Certifying machine-learning models
Shahar Segal, Yossi Adi, Benny Pinkas, Carsten Baum, Chaya Ganesh, and Joseph Keshet · 2020
Cited alongside, same era.
ECLIPSE: Enhanced compiling method for pedersen-committed zkSNARK engines
Diego F Aranha, Emil Madsen Bennedsen, Matteo Campanelli, Chaya Ganesh, Claudio Orlandi, and Akira Takahashi · 2021
Cited alongside, same era.
Lunar: A toolbox for more efficient universal and updatable zkSNARKs and commit-and-prove extensions
Matteo Campanelli, Antonio Faonio, Dario Fiore, Anaïs Querol, and Hadrián Rodríguez · 2021
Cited alongside, same era.
Customizable constraint systems for succinct arguments
Srinath Setty, Justin Thaler, and Riad Wahby · 2023
Later among the works it cites.
Confidential-PROFITT: Confidential PROof of FaIr training of trees
Ali Shahin Shamsabadi, Sierra Calanda Wyllie, Nicholas Franzese, Natalie Dullerud, Sébastien Gambs, Nicolas Papernot, Xiao Wang, and Adrian Weller · 2023
Later among the works it cites.
ZkDL: Efficient zero-knowledge proofs of deep learning training
Haochen Sun and Hongyang Zhang · 2023
Later among the works it cites.
pvcnn: Privacy-preserving and verifiable convolutional neural network testing
Jiasi Weng, Jian Weng, Gui Tang, Anjia Yang, Ming Li, and Jia-Nan Liu · 2023
Later among the works it cites.
Proving system components
Aztec Network · 2024
Closest in time.
AI auditing: The broken bus on the road to AI accountability
Abeba Birhane, Ryan Steed, Victor Ojewale, Briana Vecchione, and Inioluwa Deborah Raji · 2024
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
ZEN: An optimizing compiler for verifiable, zero-knowledge neural network inferences
Boyuan Feng, Lianke Qin, Zhenfei Zhang, Yufei Ding, and Shumo Chu · 2021
Cited alongside, same era.
Poseidon: A new hash function for zero-knowledge proof systems
Lorenzo Grassi, Dmitry Khovratovich, Christian Rechberger, Arnab Roy, and Markus Schofnegger · 2021
Cited alongside, same era.
zkCNN: Zero knowledge proofs for convolutional neural network predictions and accuracy
Tianyi Liu, Xiang Xie, and Yupeng Zhang · 2021
Cited alongside, same era.
High-resolution image synthesis with latent diffusion models
Robin Rombach, A. Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer · 2021
Cited alongside, same era.
Halo2 challenge api, 2022
Privacy & Scaling Explorations · 2022
Cited alongside, same era.
Scaling up trustless DNN inference with zero-knowledge proofs
Daniel Kang, Tatsunori Hashimoto, Ion Stoica, and Yi Sun · 2022
Cited alongside, same era.
Cryptographic auditing for collaborative learning
Hidde Lycklama, Nicolas Küchler, Alexander Viand, Emanuel Opel, Lukas Burkhalter, and Anwar Hithnawi · 2022
Cited alongside, same era.
Closest in time.
Removing additional commitment cost, 2023
EZKL Blog · 2024
Closest in time.
ZKML: An optimizing system for ML inference in zero-knowledge proofs
Bing-Jyue Chen, Suppakit Waiwitlikhit, Ion Stoica, and Daniel Kang · 2024
Closest in time.
Visibility: What is private?, 2023
EZKL Docs · 2024
Closest in time.
An engine for doing inference for deep learning models and other computational graphs in a zk-snark (ZKML)
EZKL · 2024
Closest in time.
Halo2 book, 2021
Zcash Foundation · 2024
Closest in time.
Trust the process: Zero-knowledge machine learning to enhance trust in generative AI interactions
Bianca-Mihaela Ganescu and Jonathan Passerat-Palmbach · 2024
Closest in time.
Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning
Hidde Lycklama, Alexander Viand, Nicolas Küchler, Christian Knabenhans, and Anwar Hithnawi · 2024
Closest in time.
Confidential-DPproof: Confidential proof of differentially private training
Ali Shahin Shamsabadi, Gefei Tan, Tudor Ioan Cebere, Aurélien Bellet, Hamed Haddadi, Nicolas Papernot, Xiao Wang, and Adrian Weller · 2024
Closest in time.
Verifiable evaluations of machine learning models using zkSNARKs
Tobin South, Alexander Camuto, Shrey Jain, Shayla Nguyen, Robert Mahari, Christian Paquin, Jason Morton, and Alex Pentland · 2024
Closest in time.
Trustless audits without revealing data or models
Suppakit Waiwitlikhit, Ion Stoica, Yi Sun, Tatsunori Hashimoto, and Daniel Kang · 2024
Closest in time.
VerITAS: verifying image transformations at scale
Trisha Datta, Binyi Chen, and Dan Boneh · 2025
Closest in time.
Adding zero knowledge to plonk-halo, 2020
Daniel Lubarov · 2025
Closest in time.
zkGPT: An efficient non-interactive zero-knowledge proof framework for LLM inference
Wenjie Qu, Yijun Sun, Xuanmin Liu, Ta Lu, Yanpe Guo, Kai Chen, and Jiaheng Zhang · 2025
Closest in time.