Provenance of AI-Generated Images: A Vector Similarity and Blockchain-based Approach

TL;DR

This paper introduces a new embedding-based framework utilizing vector similarity and blockchain concepts to authenticate AI-generated images, addressing challenges in digital content verification amidst advanced generative models.

Contribution

The paper presents a novel, robust, and efficient method for distinguishing AI-generated images from real ones using image embeddings and vector similarity, validated across multiple models.

Findings

Embedding proximity effectively separates AI and human images.

Moderate perturbations do not significantly affect detection accuracy.

The framework is computationally efficient and generalizable.

Abstract

Rapid advancement in generative AI and large language models (LLMs) has enabled the generation of highly realistic and contextually relevant digital content. LLMs such as ChatGPT with DALL-E integration and Stable Diffusion techniques can produce images that are often indistinguishable from those created by humans, which poses challenges for digital content authentication. Verifying the integrity and origin of digital data to ensure it remains unaltered and genuine is crucial to maintaining trust and legality in digital media. In this paper, we propose an embedding-based AI image detection framework that utilizes image embeddings and a vector similarity to distinguish AI-generated images from real (human-created) ones. Our methodology is built on the hypothesis that AI-generated images demonstrate closer embedding proximity to other AI-generated content, while human-created images cluster similarly within their domain. To validate this hypothesis, we developed a system that processes a diverse dataset of AI and human-generated images through five benchmark embedding models. Extensive experimentation demonstrates the robustness of our approach, and our results confirm that moderate to high perturbations minimally impact the embedding signatures, with perturbed images maintaining close similarity matches to their original versions. Our solution provides a generalizable framework for AI-generated image detection that balances accuracy with computational efficiency.