Score: 0

Towards the Resistance of Neural Network Watermarking to Fine-tuning

Published: May 2, 2025 | arXiv ID: 2505.01007v1

By: Ling Tang , Yuefeng Chen , Hui Xue and more

Potential Business Impact:

Protects computer brains from being copied.

Business Areas:
Darknet Internet Services

This paper proves a new watermarking method to embed the ownership information into a deep neural network (DNN), which is robust 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 watermark module to encode the watermark information to specific frequency components in a convolutional filter. Preliminary experiments demonstrate the effectiveness of our method.

Page Count
15 pages

Category
Computer Science:
Machine Learning (CS)