When Synthetic Traces Hide Real Content: Analysis of Stable Diffusion Image Laundering

TL;DR

This paper analyzes how Stable Diffusion autoencoders can be used to launder real images into synthetic-looking ones, complicating forensic detection and proposing a two-stage detection pipeline to distinguish between real, laundered, and synthetic images.

Contribution

It reveals the forensic challenges posed by SD image laundering and introduces a robust detection method to identify laundered images, addressing a critical security concern.

Findings

SD autoencoders can produce highly realistic laundered images

Laundering obscures forensic artifacts, reducing detection accuracy

Proposed detection pipeline effectively differentiates image types

Abstract

In recent years, methods for producing highly realistic synthetic images have significantly advanced, allowing the creation of high-quality images from text prompts that describe the desired content. Even more impressively, Stable Diffusion (SD) models now provide users with the option of creating synthetic images in an image-to-image translation fashion, modifying images in the latent space of advanced autoencoders. This striking evolution, however, brings an alarming consequence: it is possible to pass an image through SD autoencoders to reproduce a synthetic copy of the image with high realism and almost no visual artifacts. This process, known as SD image laundering, can transform real images into lookalike synthetic ones and risks complicating forensic analysis for content authenticity verification. Our paper investigates the forensic implications of image laundering, revealing a serious potential to obscure traces of real content, including sensitive and harmful materials that could be mistakenly classified as synthetic, thereby undermining the protection of individuals depicted. To address this issue, we propose a two-stage detection pipeline that effectively differentiates between pristine, laundered, and fully synthetic images (those generated from text prompts), showing robustness across various conditions. Finally, we highlight another alarming property of image laundering, which appears to mask the unique artifacts exploited by forensic detectors to solve the camera model identification task, strongly undermining their performance. Our experimental code is available at https://github.com/polimi-ispl/synthetic-image-detection.