Detecting AI-Generated Images via Diffusion Snap-Back Reconstruction: A Forensic Approach

TL;DR

This paper introduces a novel forensic method that detects AI-generated images by analyzing their response to diffusion model-based reconstruction, achieving high accuracy and robustness against common distortions.

Contribution

The study proposes a new diffusion snap-back reconstruction technique for detecting AI images, leveraging their response patterns, which outperforms traditional detection methods.

Findings

Achieves AUROC of 0.993 on balanced dataset

Remains stable under image compression and noise

Effective with only logistic regression classifier

Abstract

The rapid advancement of generative image models has transformed digital media to the point where AI generated images can no longer be reliably distinguished from authentic photographs by human observers or many conventional detection methods. Modern text to image systems such as Stable Diffusion and DALL E can now generate images so realistic that they often appear completely natural, leaving little to no visible artifacts for traditional deepfake detectors to rely on. This challenge has practical consequences for misinformation control, institutional identity verification, and digital trust in political and legal contexts. Instead of searching for hidden pixel level traces, we take a different approach: we observe how an image responds when it is gently disturbed and reconstructed by a diffusion model. We call this behavior diffusion snap back. By tracking how perceptual similarity measures (LPIPS, SSIM, and PSNR) change across different reconstruction strengths, we capture compact and interpretable signals that reveal how closely an image aligns with the diffusion model's learned denoising behavior. Evaluated on a balanced dataset of 4,000 human and AI generated images, the proposed method achieves an AUROC of 0.993 under stratified five fold cross validation and 0.990 on a holdout split using only logistic regression. Initial robustness tests show that the method remains stable under common real world distortions such as image compression and added noise. Although our experiments were conducted using a single diffusion backbone, the results indicate that reconstruction behavior can serve as a reliable and scalable foundation for synthetic media detection as generative models continue to grow more realistic.