# VeriLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs

arXiv: https://arxiv.org/abs/2508.21393 · HTML: https://mlsanity.com/paper/2508.21393/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 53 references that are in the map.
- First posted on arXiv 29 Aug 2025.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [zkLLM: Zero Knowledge Proofs for Large Language Models](https://mlsanity.com/paper/2404.16109/) (2024)
- [SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud](https://mlsanity.com/paper/1706.10268/) (2017)
- [Scaling up Trustless DNN Inference with Zero-Knowledge Proofs](https://mlsanity.com/paper/2210.08674/) (2022)
- [VeriML: Enabling Integrity Assurances and Fair Payments for Machine Learning as a Service](https://mlsanity.com/paper/1909.06961/) (2019)
- [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)
- [zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training](https://mlsanity.com/paper/2307.16273/) (2023)
- [Global and Local Semantic Completion Learning for Vision-Language Pre-training](https://mlsanity.com/paper/2306.07096/) (2023)
- [Drynx: Decentralized, Secure, Verifiable System for Statistical Queries and Machine Learning on Distributed Datasets](https://mlsanity.com/paper/1902.03785/) (2019)
- [A Zero Knowledge Sumcheck and its Applications](https://mlsanity.com/paper/1704.02086/) (2017)
- [ZKLoRA: Efficient Zero-Knowledge Proofs for LoRA Verification](https://mlsanity.com/paper/2501.13965/) (2025)

## Built on by (most cited first, 1 of 1)

- [Internalising the Identity Primitive: Cryptographic Individuality for an Autonomous Agent on a Public Blockchain](https://mlsanity.com/paper/2608.02986/) (2026)

## Abstract (arXiv)

Fine-tuning large language models (LLMs) is crucial for adapting them to specific tasks, yet it remains computationally demanding and raises concerns about correctness and privacy, particularly in untrusted environments. Although parameter-efficient methods like Low-Rank Adaptation (LoRA) significantly reduce resource requirements, ensuring the security and verifiability of fine-tuning under zero-knowledge constraints remains an unresolved challenge. To address this, we introduce VeriLoRA, the first framework to integrate LoRA fine-tuning with zero-knowledge proofs (ZKPs), achieving provable security and correctness. VeriLoRA employs advanced cryptographic techniques -- such as lookup arguments, sumcheck protocols, and polynomial commitments -- to verify both arithmetic and non-arithmetic operations in Transformer-based architectures. The framework provides end-to-end verifiability for forward propagation, backward propagation, and parameter updates during LoRA fine-tuning, while safeguarding the privacy of model parameters and training data. Leveraging GPU-based implementations, VeriLoRA demonstrates practicality and efficiency through experimental validation on open-source LLMs like LLaMA, scaling up to 13 billion parameters. By combining parameter-efficient fine-tuning with ZKPs, VeriLoRA bridges a critical gap, enabling secure and trustworthy deployment of LLMs in sensitive or untrusted environments.