# A Framework for Cryptographic Verifiability of End-to-End AI Pipelines

arXiv: https://arxiv.org/abs/2503.22573 · HTML: https://mlsanity.com/paper/2503.22573/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 66 references that are in the map.
- First posted on arXiv 28 Mar 2025.

## Builds on (most cited first, 20 of 20)

- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Machine Unlearning: Solutions and Challenges](https://mlsanity.com/paper/2308.07061/) (2023)
- [LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report](https://mlsanity.com/paper/2405.00732/) (2024)
- [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)
- [Verifiable and Provably Secure Machine Unlearning](https://mlsanity.com/paper/2210.09126/) (2022)
- [Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning](https://mlsanity.com/paper/2202.03460/) (2022)
- [zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training](https://mlsanity.com/paper/2307.16273/) (2023)
- [Fairness, Integrity, and Privacy in a Scalable Blockchain-based Federated Learning System](https://mlsanity.com/paper/2111.06290/) (2021)
- [Verifiable evaluations of machine learning models using zkSNARKs](https://mlsanity.com/paper/2402.02675/) (2024)
- [Trustless Audits without Revealing Data or Models](https://mlsanity.com/paper/2404.04500/) (2024)
- [FairProof : Confidential and Certifiable Fairness for Neural Networks](https://mlsanity.com/paper/2402.12572/) (2024)
- [martFL: Enabling Utility-Driven Data Marketplace with a Robust and Verifiable Federated Learning Architecture](https://mlsanity.com/paper/2309.01098/) (2023)
- [ezDPS: An Efficient and Zero-Knowledge Machine Learning Inference Pipeline](https://mlsanity.com/paper/2212.05428/) (2022)
- [DECORAIT -- DECentralized Opt-in/out Registry for AI Training](https://mlsanity.com/paper/2309.14400/) (2023)
- [Secure and Confidential Certificates of Online Fairness](https://mlsanity.com/paper/2410.02777/) (2024)
- [VeriDL: Integrity Verification of Outsourced Deep Learning Services (Extended Version)](https://mlsanity.com/paper/2107.00495/) (2021)
- [ZK-IMG: Attested Images via Zero-Knowledge Proofs to Fight Disinformation](https://mlsanity.com/paper/2211.04775/) (2022)
- [Distributed Ledger for Provenance Tracking of Artificial Intelligence Assets](https://mlsanity.com/paper/2002.11000/) (2020)
- [PDFed: Privacy-Preserving and Decentralized Asynchronous Federated Learning for Diffusion Models](https://mlsanity.com/paper/2409.18245/) (2024)

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

- [RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies](https://mlsanity.com/paper/2603.11001/) (2026)
- [AI Models Can Provably Hide Arbitrary Capabilities](https://mlsanity.com/paper/2610.13928/) (2026)

## Abstract (arXiv)

The increasing integration of Artificial Intelligence across multiple industry sectors necessitates robust mechanisms for ensuring transparency, trust, and auditability of its development and deployment. This topic is particularly important in light of recent calls in various jurisdictions to introduce regulation and legislation on AI safety. In this paper, we propose a framework for complete verifiable AI pipelines, identifying key components and analyzing existing cryptographic approaches that contribute to verifiability across different stages of the AI lifecycle, from data sourcing to training, inference, and unlearning. This framework could be used to combat misinformation by providing cryptographic proofs alongside AI-generated assets to allow downstream verification of their provenance and correctness. Our findings underscore the importance of ongoing research to develop cryptographic tools that are not only efficient for isolated AI processes, but that are efficiently `linkable' across different processes within the AI pipeline, to support the development of end-to-end verifiable AI technologies.