AI model disgorgement: Methods and choices
Open Access
- 19 April 2024
- journal article
- research article
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 121 (18)
Abstract
Over the past few years, machine learning models have significantly increased in size and complexity, especially in the area of generative AI such as large language models. These models require massive amounts of data and compute capacity to train, to the extent that concerns over the training data (such as protected or private content) cannot be practically addressed by retraining the model “from scratch” with the questionable data removed or altered. Furthermore, despite significant efforts and controls dedicated to ensuring that training corpora are properly curated and composed, the sheer volume required makes it infeasible to manually inspect each datum comprising a training corpus. One potential approach to training corpus data defects is model disgorgement, by which we broadly mean the elimination or reduction of not only any improperly used data, but also the effects of improperly used data on any component of an ML model. Model disgorgement techniques can be used to address a wide range of issues, such as reducing bias or toxicity, increasing fidelity, and ensuring responsible use of intellectual property. In this paper, we survey the landscape of model disgorgement methods and introduce a taxonomy of disgorgement techniques that are applicable to modern ML systems. In particular, we investigate the various meanings of “removing the effects” of data on the trained model in a way that does not require retraining from scratch.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- SAFE: Machine Unlearning With Shard Graphs2023
- Mixed Differential Privacy in Computer Vision2022
- Exploring user historical semantic and sentiment preference for microblog sentiment classificationNeurocomputing, 2021
- Positive-Congruent Training: Towards Regression-Free Model Updates2021
- Mixed-Privacy Forgetting in Deep Networks2021
- Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations2020
- Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks2020
- Towards Backward-Compatible Representation Learning2020
- Universal Adversarial Perturbations2017
- Change Blindness: Implications for the Nature of Visual Attention2001