Newest papers

BrushOff: Stroke-Based Re-rendering as a Watermark Removal Attack on Painting

Hao Chen, Junnan Xu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26682 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

La sonda se utiliza para marcar quién posee una pintura. Mostramos que un simple ataque elimina la propiedad más robusta que probamos. La sonda de ataque recrea la pintura con marca de agua con golpes de cepillo, utilizando un render baseado en golpes pre-entrenado. Llamamos a este ataque BrushOff. No necesita entrenamiento, ningún conocimiento de la marca de agua, y ningún modelo generativo. Testamos cuatro marcas de agua en 500 pinturas de cinco estilos. VINE, una marca de agua reciente construida para sobrevivir a la edición de imagen, sobrevive a todas las 14 distorsiones convencionales que probamos, con al menos 97.8% de detección. Benpainters rebasa su detección al 1,8%, mientras que la salida mantiene una puntuación de calidad sin referencia cercana a la de las pinturas limpias. La regeneración

Machine translation (Meta M2M100); the English original follows.

Abstract

Invisible watermarks are used to mark who owns a painting. We show that a simple attack removes the most robust one we test. The attack redraws the watermarked painting with brush strokes, using a pretrained stroke-based renderer. We call this attack BrushOff. It needs no training, no knowledge of the watermark, and no generative model. We test four watermarks on 500 paintings from five styles. VINE, a recent watermark built to survive image editing, survives all 14 conventional distortions we test, with at least 97.8% detection. Repainting lowers its detection to 1.8%, while the output keeps a no-reference quality score close to that of the clean paintings. Diffusion regeneration can also remove VINE, but at the same removal level it moves the image twice as far from the painting in DreamSim distance, and it changes what the painting shows. Because the renderer draws a countable number of strokes, we can control the attack strength step by step. Finally, we test what kind of signal survives. A simple probe that stores bits in the relative brightness of neighboring regions survives repainting, while a probe that uses absolute brightness does not. The same probe fails under diffusion regeneration, while VINE fails under repainting. Robustness to these two attacks is therefore a separate property, and benchmarks should test both.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Robustness (evolution), Artificial intelligence, Painting, Watermark, Computer vision

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange