Alexander N. Gorban — accepted AI-conference papers

2025

Staining and Locking Computer Vision Models Without Retraining

Oliver J. Sutton, Qinghua Zhou, George Leete, Alexander N. Gorban, Ivan Y. Tyukin

ICCV 2025poster

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 trig…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Stealth edits to large language models

Oliver Sutton, Qinghua Zhou, Wei Wang, Desmond Higham, Alexander N. Gorban, Alexander Bastounis +1

NeurIPS 2024poster

We reveal the theoretical foundations of techniques for editing large language models, and present new methods which can do so without requiring retraining. Our theoretical insights show that a single metric (a measure of the intrinsic dimension of the model's features) can be used to assess a model…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗