# Machine Learning Model Attribution Challenge

arXiv: https://arxiv.org/abs/2302.06716 · HTML: https://mlsanity.com/paper/2302.06716/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 11 references that are in the map.
- First posted on arXiv 13 Feb 2023.

## Builds on (most cited first, 6 of 6)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Automatic Detection of Generated Text is Easiest when Humans are Fooled](https://mlsanity.com/paper/1911.00650/) (2019)
- [Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations](https://mlsanity.com/paper/2301.04246/) (2023)
- [Generating Steganographic Text with LSTMs](https://mlsanity.com/paper/1705.10742/) (2017)
- [Artificial Interrogation for Attributing Language Models](https://mlsanity.com/paper/2211.10877/) (2022)

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

- [A Cost Analysis of Generative Language Models and Influence Operations](https://mlsanity.com/paper/2308.03740/) (2023)
- [What can we learn from Data Leakage and Unlearning for Law?](https://mlsanity.com/paper/2307.10476/) (2023)

## Abstract (arXiv)

We present the findings of the Machine Learning Model Attribution Challenge. Fine-tuned machine learning models may derive from other trained models without obvious attribution characteristics. In this challenge, participants identify the publicly-available base models that underlie a set of anonymous, fine-tuned large language models (LLMs) using only textual output of the models. Contestants aim to correctly attribute the most fine-tuned models, with ties broken in the favor of contestants whose solutions use fewer calls to the fine-tuned models' API. The most successful approaches were manual, as participants observed similarities between model outputs and developed attribution heuristics based on public documentation of the base models, though several teams also submitted automated, statistical solutions.