From Detection to Localization: A Unified Forensics Framework for Fully Synthetic and Tampered Images

2026-09-02

AI Summary

为解决生成模型导致的图像伪造检测问题，本文提出一个统一的多分类框架，不仅能鉴别图像真实性，还能通过分割分支实现篡改区域的像素级定位。

Abstract

The rapid advancement of generative models has significantly worsened the problem of manipulated image detection, as these methods are capable of producing highly realistic forgeries, reinforcing the importance of multimedia forensics. Conventional approaches typically frame image manipulation detection as a binary classification task (real vs. generated), which limits the capability to distinguish and localize different forms of manipulation. To address these constraints, this work extends an existing detector by introducing a unified multiclass framework (real vs. fully generated vs. tampered). In addition to classifying image authenticity, the framework incorporates a segmentation branch to enable pixel-level localization of tampered regions. The proposed approach outperforms selected recent benchmarks, offering an efficient solution with improved classification accuracy and higher IoU scores for the localization task. Find the code at https://github.com/anngal01/From-Detection-to-Localization-A-Unified-Forensics-Framework-for-Fully-Synthetic-and-Tampered-Images.

Problem

• image manipulation detection
• generative models
• multimedia forensics
• tampered images

Innovation

• unified framework
• multiclass classification
• pixel-level localization
• segmentation branch