APT: Anchor-aligned Perturbations for Tamper Localization in Fully Regenerated Images

2026-08-31

AI Summary

为解决全再生图像篡改定位问题，提出APT方法，通过半脆弱潜空间扰动和特征向量对齐差异检测篡改。

Abstract

Proactive tamper localization embeds an imperceptible signal into an image prior to distribution, enabling pixel-level manipulation detection. Existing methods assume a spliced (SP) setting, where synthesized regions are composited onto the original background, leaving embedded signals intact. However, real-world diffusion-based inpainting operates in a fully regenerated (FR) setting, where the entire image undergoes denoising, disrupting background signals and rendering existing frameworks ineffective. We propose APT, a semi-fragile latent-space perturbation that embeds a dense, vector-wise localization signal. By aligning each spatial feature vector toward a fixed anchor direction, APT localizes tampering via the alignment disparity between synthesized foreground and anchor-aligned background features after inpainting. The proposed hard negative mining loss and noisy perturbation branch further enforce uniform alignment. Experiments on COCO demonstrate that APT achieves an FR IoU of 0.92, outperforming the strongest baseline (WAM, 0.84), while existing methods collapse to near-random performance (AUC 0.5), establishing APT as a practical forensic framework generalizable across tampering types unknown at test time.

Problem

• tamper localization
• fully regenerated images
• signal disruption
• inpainting

Innovation

• Anchor-aligned Perturbations
• Fully Regenerated Images
• Semi-fragile Latent-space Perturbation
• Hard Negative Mining Loss
• Noisy Perturbation Branch