# Atlas: A Framework for ML Lifecycle Provenance & Transparency

arXiv: https://arxiv.org/abs/2502.19567 · HTML: https://mlsanity.com/paper/2502.19567/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 26 of its 100 references that are in the map.
- First posted on arXiv 26 Feb 2025.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 26 of 26)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Certified Defenses for Data Poisoning Attacks](https://mlsanity.com/paper/1706.03691/) (2017)
- [Poisoning Web-Scale Training Datasets is Practical](https://mlsanity.com/paper/2302.10149/) (2023)
- [High Accuracy and High Fidelity Extraction of Neural Networks](https://mlsanity.com/paper/1909.01838/) (2019)
- [OpenFL: An open-source framework for Federated Learning](https://mlsanity.com/paper/2105.06413/) (2021)
- [A Systematic Review on Model Watermarking for Neural Networks](https://mlsanity.com/paper/2009.12153/) (2020)
- [Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges](https://mlsanity.com/paper/1905.04223/) (2019)
- [The AI Community Building the Future? A Quantitative Analysis of Development Activity on Hugging Face Hub](https://mlsanity.com/paper/2405.13058/) (2024)
- [Machine Learning with Confidential Computing: A Systematization of Knowledge](https://mlsanity.com/paper/2208.10134/) (2022)
- [Laminator: Verifiable ML Property Cards using Hardware-assisted Attestations](https://mlsanity.com/paper/2406.17548/) (2024)
- [Examining the Impact of Provenance-Enabled Media on Trust and Accuracy Perceptions](https://mlsanity.com/paper/2303.12118/) (2023)
- [AMP: Authentication of Media via Provenance](https://mlsanity.com/paper/2001.07886/) (2020)
- [Attestation Mechanisms for Trusted Execution Environments Demystified](https://mlsanity.com/paper/2206.03780/) (2022)
- [Machine Learning Robustness: A Primer](https://mlsanity.com/paper/2404.00897/) (2024)
- [Reproducible Builds: Increasing the Integrity of Software Supply Chains](https://mlsanity.com/paper/2104.06020/) (2021)
- [Certification for Differentially Private Prediction in Gradient-Based Training](https://mlsanity.com/paper/2406.13433/) (2024)
- [Fortify Your Foundations: Practical Privacy and Security for Foundation Model Deployments In The Cloud](https://mlsanity.com/paper/2410.05930/) (2024)
- [Beyond Detection: Unveiling Fairness Vulnerabilities in Abusive Language Models](https://mlsanity.com/paper/2311.09428/) (2023)
- [Trustworthy confidential virtual machines for the masses](https://mlsanity.com/paper/2402.15277/) (2024)
- [Building secure distributed applications the DECENT way](https://mlsanity.com/paper/2004.02020/) (2020)
- [Mithridates: Auditing and Boosting Backdoor Resistance of Machine Learning Pipelines](https://mlsanity.com/paper/2302.04977/) (2023)

## Built on by (most cited first, 8 of 8)

- [AIBoMGen: Generating an AI Bill of Materials for Secure, Transparent, and Compliant Model Training](https://mlsanity.com/paper/2601.05703/) (2026)
- [Safeguarding LLM Agents from Misalignment through Provenance Analysis](https://mlsanity.com/paper/2607.01236/) (2026)
- [Operationalising Artificial Intelligence Bills of Materials (AIBOMs) for Verifiable AI Provenance and Lifecycle Assurance](https://mlsanity.com/paper/2605.19755/) (2026)
- [Scalable GPU-Based Integrity Verification for Large Machine Learning Models](https://mlsanity.com/paper/2510.23938/) (2025)
- [Threat Modeling for AI: The Case for an Asset-Centric Approach](https://mlsanity.com/paper/2505.06315/) (2025)
- [A Blueprint for Self-Evolving Coding Agents in Vehicle Aerodynamic Drag Prediction](https://mlsanity.com/paper/2603.21698/) (2026)
- [A Large-Scale Measurement of AI Bill of Materials Completeness in Hugging Face Models](https://mlsanity.com/paper/2607.17242/) (2026)
- [Position: AI Governance Needs ISO-like Interoperability Protocols, Not Just Laws](https://mlsanity.com/paper/2608.14568/) (2026)

## Abstract (arXiv)

The rapid adoption of open source machine learning (ML) datasets and models exposes today's AI applications to critical risks like data poisoning and supply chain attacks across the ML lifecycle. With growing regulatory pressure to address these issues through greater transparency, ML model vendors face challenges balancing these requirements against confidentiality for data and intellectual property needs. We propose Atlas, a framework that enables fully attestable ML pipelines. Atlas leverages open specifications for data and software supply chain provenance to collect verifiable records of model artifact authenticity and end-to-end lineage metadata. Atlas combines trusted hardware and transparency logs to enhance metadata integrity, preserve data confidentiality, and limit unauthorized access during ML pipeline operations, from training through deployment. Our prototype implementation of Atlas integrates several open-source tools to build an ML lifecycle transparency system, and assess the practicality of Atlas through two case study ML pipelines.