{"ID":2889309,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.22000","arxiv_id":"2507.22000","title":"Staining and locking computer vision models without retraining","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.","short_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...","url_abs":"https://arxiv.org/abs/2507.22000","url_pdf":"https://arxiv.org/pdf/2507.22000v1","authors":"[\"Oliver J. Sutton\",\"Qinghua Zhou\",\"George Leete\",\"Alexander N. Gorban\",\"Ivan Y. Tyukin\"]","published":"2025-07-29T16:47:34Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}