Spectral characteristics of autoencoder parameters as a vector representation of data
What a neural network's weights reveal about the data it learned from
A trained autoencoder's internal parameters contain a fingerprint of the data it learned from. Researchers showed that by analyzing the mathematical structure of these parameters—specifically their singular values—you can tell which datasets a model was trained on with high accuracy, without ever looking at the original data or using complicated reconstruction methods.
This could let researchers quickly identify what data a neural network has seen, which matters for detecting model theft, understanding training data composition, and auditing AI systems for bias or unwanted memorization. It also suggests a simpler way to compare and categorize trained models based on their internals alone.