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

arXiv:2608.30656v1 Announce Type: new 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.

Related

• GAP-SAM: A Global Artifact Prior for Generalizable AI-Generated Image Manipulation Localization
• LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization
• ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation

Source: arXiv cs.CV | 2026-09-01