Semantic Color Naturalness Breaker: Preventing Illegitimate Colorization via Content-Aware Color Priors

2026-07-20

AI Summary

This work proposes a Semantic-level Colorization-Nonviable Benchmark (SCNB) framework to protect grayscale images from unauthorized automatic colorization by embedding imperceptible perturbations that mislead colorization models into producing semantically inconsistent colors, thereby degrading the naturalness of illicit outputs while preserving visual fidelity. The approach introduces CaCDD, a novel reference-free, semantics-aware metric for assessing color plausibility, and integrates adversarial perturbation generation with a multi-model ensemble strategy for optimization. Experimental results demonstrate that SCNB effectively thwarts state-of-the-art colorization models on ImageNet under small perturbation budgets, exhibits robustness against common post-processing operations, and shows strong potential for real-world deployment.

Abstract

Automatic image colorization enables large-scale and low-cost reuse of grayscale media (e.g., manga panels and archival photographs), facilitating unauthorized reuse and redistribution. Once released online, grayscale content can be readily turned into unauthorized colorized derivatives using off-the-shelf models, creating a practical need for proactive, content-side protection at publication time. Building on Uncolorable Examples (UE), which add imperceptible perturbations to released grayscale images to degrade unauthorized colorization, we propose Semantic Color Naturalness Breaker (SCNB) -- a semantic-level UE framework that drives colorization outputs toward content-inconsistent colors while preserving the visual fidelity of the released grayscale media. We further introduce Content-aware Color Distributional Distance (CaCDD), a ground-truth-free, content-aware measure of color plausibility derived from semantic color priors, used both as the optimization objective of SCNB and as an evaluation metric. Experiments on ImageNet show that our method remains effective under small perturbation budgets and common post-processing, supporting practical deployment in real-world content-sharing pipelines.

Problem

• image colorization
• unauthorized reuse
• content protection
• semantic color priors
• grayscale media

Innovation

• Semantic Color Naturalness Breaker
• Uncolorable Examples
• Content-aware Color Priors
• CaCDD
• Image Colorization Protection