BIMW: Blockchain-Enabled Innocuous Model Watermarking for Secure Ownership Verification
Xinyun Liu, Ronghua Xu · Preprints.org · 2025
The integration of Artificial Intelligence (AI) and edge computing gives rise to Edge Intelligence (EI), which offers effective solutions to the limitations of traditional cloud-based AI; however, deploying models across distributed edge platforms raises concerns regarding authenticity, thereby necessitating robust mechanisms for ownership verification. Currently, backdoor-based model watermarking techniques represent a state-of-the-art approach for ownership verification; however, their reliance on model poisoning introduces potential security risks and unintended behaviors. To solve this challenge, we propose BIMW, a blockchain-enabled innocuous model watermarking framework that ensures secure and trustworthy AI model deployment and sharing in distributed edge computing environments. Unlike widely applied backdoor-based watermarking methods, BIMW adopts a novel innocuous model watermarking method called Interpretable Watermarking (IW), which embeds ownership information without compromising model integrity or functionality. In addition, BIMW integrates a blockchain security fabric to ensure the integrity and auditability of the watermarked data during storage and sharing. Extensive experiments are conducted on a Jetson Orin Nano board, which simulates edge computing environments. The results demonstrate our framework's superior performance in terms of effectiveness and innocuousness, as well as its robustness against potential model watermarking attacks.