Provenance Verification of AI-Generated Images via a Perceptual Hash Registry Anchored on Blockchain
Apoorv Mohit, Bhavya Aggarwal, Chinmay Gondhalekar
TL;DR
The paper tackles scalable provenance verification for AI-generated images by introducing a blockchain-backed, registry-based framework that uses perceptual hashing to fingerprint images. It couples on-chain cryptographic commitments via a Merkle Patricia Trie with off-chain BK-trees for efficient similarity search, enabling exact and near-duplicate matching at upload time while keeping on-chain storage minimal. Through experiments, it demonstrates that a 137-prefix search with 2-bit expansion and a threshold around $\tau=6$ achieves high recall (≈98–99%) with low false positives, and that the combined MPT+BK-tree index maintains sub-millisecond tail latency up to one million entries. The approach complements watermarking and learning-based detectors, offering a transparent, scalable provenance signal suitable for platform-level deployment and cross-platform interoperability. It lays a foundation for future extensions to multi-modal content, hybrid hashing, and federated blockchain trust infrastructures.
Abstract
The rapid advancement of artificial intelligence has made the generation of synthetic images widely accessible, increasing concerns related to misinformation, digital forgery, and content authenticity on large-scale online platforms. This paper proposes a blockchain-backed framework for verifying AI-generated images through a registry-based provenance mechanism. Each AI-generated image is assigned a digital fingerprint that preserves similarity using perceptual hashing and is registered at creation time by participating generation platforms. The hashes are stored on a hybrid on-chain/off-chain public blockchain using a Merkle Patricia Trie for tamper-resistant storage (on-chain) and a Burkhard-Keller tree (off-chain) to enable efficient similarity search over large image registries. Verification is performed when images are re-uploaded to digital platforms such as social media services, enabling identification of previously registered AI-generated images even after benign transformations or partial modifications. The proposed system does not aim to universally detect all synthetic images, but instead focuses on verifying the provenance of AI-generated content that has been registered at creation time. By design, this approach complements existing watermarking and learning-based detection methods, providing a platform-agnostic, tamper-proof mechanism for scalable content provenance and authenticity verification at the point of large-scale online distribution.