# Uncolorable Examples: Preventing Unauthorized AI Colorization via Perception-Aware Chroma-Restrictive Perturbation

arXiv: https://arxiv.org/abs/2510.08979 · HTML: https://mlsanity.com/paper/2510.08979/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Countering Adversarial Images using Input Transformations](https://mlsanity.com/paper/1711.00117/) (2017)
- [Mitigating Adversarial Effects Through Randomization](https://mlsanity.com/paper/1711.01991/) (2017)
- [CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes](https://mlsanity.com/paper/2105.10872/) (2021)
- [Towards Vivid and Diverse Image Colorization with Generative Color Prior](https://mlsanity.com/paper/2108.08826/) (2021)
- [Anti-Forgery: Towards a Stealthy and Robust DeepFake Disruption Attack via Adversarial Perceptual-aware Perturbations](https://mlsanity.com/paper/2206.00477/) (2022)
- [DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders](https://mlsanity.com/paper/2212.11613/) (2022)
- [BigColor: Colorization using a Generative Color Prior for Natural Images](https://mlsanity.com/paper/2207.09685/) (2022)
- [UniColor: A Unified Framework for Multi-Modal Colorization with Transformer](https://mlsanity.com/paper/2209.11223/) (2022)

## Built on by (most cited first, 1 of 1)

- [Semantic Color Naturalness Breaker: Preventing Illegitimate Colorization via Content-Aware Color Priors](https://mlsanity.com/paper/2607.17610/) (2026)

## Abstract (arXiv)

AI-based colorization has shown remarkable capability in generating realistic color images from grayscale inputs. However, it poses risks of copyright infringement -- for example, the unauthorized colorization and resale of monochrome manga and films. Despite these concerns, no effective method currently exists to prevent such misuse. To address this, we introduce the first defensive paradigm, Uncolorable Examples, which embed imperceptible perturbations into grayscale images to invalidate unauthorized colorization. To ensure real-world applicability, we establish four criteria: effectiveness, imperceptibility, transferability, and robustness. Our method, Perception-Aware Chroma-Restrictive Perturbation (PAChroma), generates Uncolorable Examples that meet these four criteria by optimizing imperceptible perturbations with a Laplacian filter to preserve perceptual quality, and applying diverse input transformations during optimization to enhance transferability across models and robustness against common post-processing (e.g., compression). Experiments on ImageNet and Danbooru datasets demonstrate that PAChroma effectively degrades colorization quality while maintaining the visual appearance. This work marks the first step toward protecting visual content from illegitimate AI colorization, paving the way for copyright-aware defenses in generative media.