# textttRange-Arithmetic: Verifiable Deep Learning Inference on an Untrusted Party

arXiv: https://arxiv.org/abs/2505.17623 · HTML: https://mlsanity.com/paper/2505.17623/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 41 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 4 of 4)

- [SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud](https://mlsanity.com/paper/1706.10268/) (2017)
- [A Survey of Zero-Knowledge Proof Based Verifiable Machine Learning](https://mlsanity.com/paper/2502.18535/) (2025)
- [pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testing](https://mlsanity.com/paper/2201.09186/) (2022)
- [Artemis: Efficient Commit-and-Prove SNARKs for zkML](https://mlsanity.com/paper/2409.12055/) (2024)

## Built on by (most cited first, 2 of 2)

- [Game of Coding: Coding Theory in the Presence of Rational Adversaries, Motivated by Decentralized Machine Learning](https://mlsanity.com/paper/2601.02313/) (2026)
- [ServeGuard: Verifiable, Bounded-Residual Confinement of Operator-Invisible Channels Without Revealing the Certified Read Factor](https://mlsanity.com/paper/2609.21515/) (2026)

## Abstract (arXiv)

Verifiable computing (VC) has gained prominence in decentralized machine learning systems, where resource-intensive tasks like deep neural network (DNN) inference are offloaded to external participants due to blockchain limitations. This creates a need to verify the correctness of outsourced computations without re-execution. We propose textttRange-Arithmetic, a novel framework for efficient and verifiable DNN inference that transforms non-arithmetic operations, such as rounding after fixed-point matrix multiplication and ReLU, into arithmetic steps verifiable using sum-check protocols and concatenated range proofs. Our approach avoids the complexity of Boolean encoding, high-degree polynomials, and large lookup tables while remaining compatible with finite-field-based proof systems. Experimental results show that our method not only matches the performance of existing approaches, but also reduces the computational cost of verifying the results, the computational effort required from the untrusted party performing the DNN inference, and the communication overhead between the two sides.