GenShield: Unified Detection and Artifact Correction for AI-Generated Images

TL;DR

GenShield is a unified framework that jointly detects AI-generated images and performs artifact correction to restore realistic appearance, advancing digital forensics and content verification.

Contribution

It introduces a novel autoregressive model for explainable detection and controllable correction, along with a curriculum learning strategy and a new dataset.

Findings

Achieves state-of-the-art detection and correction performance.

Demonstrates strong generalization across benchmarks.

Provides a new dataset for artifact restoration evaluation.

Abstract

Diffusion-based image synthesis has made AI-generated images (AIGI) increasingly photorealistic, raising urgent concerns about authenticity in applications such as misinformation detection, digital forensics, and content moderation. Despite the substantial advances in AIGI detection, how to correct detected AI-generated images with visible artifacts and restore realistic appearance remains largely underexplored. Moreover, few existing work has established the connection between AIGI detection and artifact correction. To fill this gap, we propose GenShield, a unified autoregressive framework that jointly performs explainable AIGI detection and controllable artifact correction in a closed loop from diagnosis to restoration, revealing a mutually reinforcing relationship between these two tasks. We further introduce a Visual Chain-of-Thought based curriculum learning strategy that enables self-explained, multi-step ``diagnose-then-repair'' correction with an explicit stopping criterion. A high-quality dataset with large-scale ``artifact-restored'' pairs is also constructed alongside a unified evaluation pipeline. Extensive experiments on our correction benchmark and mainstream AIGI detection benchmarks demonstrate state-of-the-art performance and strong generalization of our method. The code is available at https://github.com/zhipeixu/GenShield.