Staining and locking computer vision models without retraining
Year: 2025
Type: preprint
Abstract: We introduce new methods of staining and locking computer vision models, to protect their owners' intellectual property. Staining, also known as watermarking, embeds secret behaviour into a model which can later be used to identify it, while locking aims to make a model unusable unless a secret trigger is inserted into input images. Unlike existing methods, our algorithms can be used to stain and lock pre-trained models without requiring fine-tuning or retraining, and come with provable, computable guarantees bounding their worst-case false positive rates. The stain and lock are implemented by directly modifying a small number of the model's weights and have minimal impact on the (unlocked) model's performance. Locked models are unlocked by inserting a small `trigger patch' into the corner of the input image. We present experimental results showing the efficacy of our methods and demonstrating their practical performance on a variety of computer vision models.
Source: arXiv (Cornell University)
Authors: Sutton, Oliver J., Zhou, Qinghua, Leete, George, Gorban, Alexander N., Tyukin, Ivan Y.
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6891920096
Cites:
Cited by:
Related to: