Towards the Resistance of Neural Network Fingerprinting to Fine-tuning
Ling Tang, YueFeng Chen, Hui Xue, Quanshi Zhang
Abstract
This paper proves a new fingerprinting method to embed the ownership information into a deep neural network (DNN) with theoretically guaranteed robustness to fine-tuning. Specifically, we prove that when the input feature of a convolutional layer only contains low-frequency components, specific frequency components of the convolutional filter will not be changed by gradient descent during the fine-tuning process, where we propose a revised Fourier transform to extract frequency components from the convolutional filter. Additionally, we also prove that these frequency components are equivariant to weight scaling and weight permutations. In this way, we design a fingerprint module to embed the fingerprint information into specific frequency components of convolutional filters. Preliminary experiments demonstrate the effectiveness of our method.
BibTeX
@inproceedings{
tang2025towards,
title={Towards the Resistance of Neural Network Fingerprinting to Fine-tuning},
author={Ling Tang and YueFeng Chen and Hui Xue and Quanshi Zhang},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=IV6JqdW0BE}
}