Amazon patents method to check AI fairness without exposing private data
Amazon has patented a technique for training artificial intelligence models that checks if the system treats different groups of people fairly. Instead of looking at sensitive personal information, the method uses a second AI model to predict fairness based on the first model's internal settings and error rates.
In the filing’s own words
Devices and techniques are generally described for privacy preserving fairness regularization for machine learning. In some examples, a first machine learning model may be trained for a first predictive task using unrestricted data. First data classified as restricted data may be determined. A second machine learning model may be trained to predict model fairness based at least in part on the first data and further based at least in part on second data representing characteristics of the first machine learning model during training. The second machine learning model may generate third data representing model fairness of a third machine learning model.
What exactly they claim (claim 1)
1. A computer-implemented method comprising: generating, by at least one processor, a first trained machine learning model by training a first machine learning model using a first dataset, wherein the first dataset comprises unrestricted data; determining first data classified as restricted data, wherein the restricted data identifies different classes of data points of the first dataset; determining second data comprising error statistics determined from the training of the first machine learning model; determining third data describing weights of the first trained machine learning model; determining fourth data representing a fairness score for the first trained machine learning model, wherein the fourth data is determined based on respective model performance for the different classes of the data points of the first dataset; generating a first training instance comprising the second data, the third data, and the fourth data; and generating a second trained machine learning model using the first training instance, wherein the second trained machine learning model is trained to predict model fairness scores from input data representing input error statistics and input model weights.
Facts
- Company
- Amazon (Amazon Technologies, Inc.)
- Official title
- Training machine learning models using privacy preserving fairness regularization
- Patent number
- US12755201B1
- Application number
- 18196158
- Filed
- May 11, 2023
- Granted
- Oct 6, 2026
- Inventors
- 2
- Claims
- 20
Classified under
G06N 20/00 Physics & computingMore from Amazon in AI & software
- Amazon patents system that cites sources for AI answers Sep 29, 2026
- Amazon patents tech to swap words in movies using actor's voice Sep 8, 2026
- Amazon patents ML tool to add graphics to live sports from moving cameras Sep 15, 2026
- Amazon patents shopping assistant that remembers your search filters Oct 6, 2026
- Amazon patents system where AI agents split tasks and talk to each other Oct 20, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.