Lost in Edits? A $\lambda$-Compass for AIGC Provenance

TL;DR

This paper introduces LambdaTracer, a latent-space attribution method that effectively detects and differentiates authentic images from manipulated ones across various editing tools, enhancing content authenticity verification.

Contribution

The paper presents LambdaTracer, a novel attribution technique that works without modifying existing pipelines and adapts to diverse iterative editing processes for robust content provenance.

Findings

LambdaTracer outperforms baseline methods in identifying manipulated images.

Effective across automated and manual editing tools like InstructPix2Pix, ControlNet, and Photoshop.

Provides a practical solution for safeguarding content authenticity in AI ecosystems.

Abstract

Recent advancements in diffusion models have driven the growth of text-guided image editing tools, enabling precise and iterative modifications of synthesized content. However, as these tools become increasingly accessible, they also introduce significant risks of misuse, emphasizing the critical need for robust attribution methods to ensure content authenticity and traceability. Despite the creative potential of such tools, they pose significant challenges for attribution, particularly in adversarial settings where edits can be layered to obscure an image's origins. We propose LambdaTracer, a novel latent-space attribution method that robustly identifies and differentiates authentic outputs from manipulated ones without requiring any modifications to generative or editing pipelines. By adaptively calibrating reconstruction losses, LambdaTracer remains effective across diverse iterative editing processes, whether automated through text-guided editing tools such as InstructPix2Pix and ControlNet or performed manually with editing software such as Adobe Photoshop. Extensive experiments reveal that our method consistently outperforms baseline approaches in distinguishing maliciously edited images, providing a practical solution to safeguard ownership, creativity, and credibility in the open, fast-evolving AI ecosystems.