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

Korean

우리는 단순한 공격이 우리가 테스트하는 가장 강력한 속성을 제거한다는 것을 보여줍니다. 공격 탐사는 사전 훈련 된 스트로크 기반 렌더링을 사용하여 사전 훈련 된 스트로크 기반 렌더링을 사용합니다. 우리는이 공격을 브러쉬 오프라고 부릅니다. 그것은 그림을 소유하고 있지 않은 훈련을 필요로하지 않으며 생성 모델을 필요로하지 않습니다. 우리는 5 가지 스타일에서 500 개의 그림에서 4 개의 워터 마크를 테스트합니다. VINE, 최근의 워터 마크는 이미지를 편집하기 위해 구축되었지만, 우리는 적어도 97.8%의 감지로 동일한 14 개의 전통적인 왜곡 테스트를 살아남습니다. Benpainting는 탐지량을 1.8 %로 낮추고

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