EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection

TL;DR

EditGuard introduces a unified image watermarking framework that simultaneously protects copyright and localizes tampering in AI-generated images, ensuring high accuracy and generalizability across various editing methods.

Contribution

It proposes a novel proactive forensics framework that unifies copyright protection and tamper localization, decoupling training from tampering types and enhancing robustness.

Findings

Balances tamper localization accuracy and copyright recovery

Generalizes well to various AIGC-based tampering methods

Effective in detecting subtle, hard-to-spot forgeries

Abstract

In the era where AI-generated content (AIGC) models can produce stunning and lifelike images, the lingering shadow of unauthorized reproductions and malicious tampering poses imminent threats to copyright integrity and information security. Current image watermarking methods, while widely accepted for safeguarding visual content, can only protect copyright and ensure traceability. They fall short in localizing increasingly realistic image tampering, potentially leading to trust crises, privacy violations, and legal disputes. To solve this challenge, we propose an innovative proactive forensics framework EditGuard, to unify copyright protection and tamper-agnostic localization, especially for AIGC-based editing methods. It can offer a meticulous embedding of imperceptible watermarks and precise decoding of tampered areas and copyright information. Leveraging our observed fragility and locality of image-into-image steganography, the realization of EditGuard can be converted into a united image-bit steganography issue, thus completely decoupling the training process from the tampering types. Extensive experiments demonstrate that our EditGuard balances the tamper localization accuracy, copyright recovery precision, and generalizability to various AIGC-based tampering methods, especially for image forgery that is difficult for the naked eye to detect. The project page is available at https://xuanyuzhang21.github.io/project/editguard/.