Q-Tag: Watermarking Quantum Circuit Generative Models

2026-02-26

AI Summary

This work addresses the vulnerability of Quantum Circuit Generation Models (QCGMs) deployed on cloud platforms to intellectual property leakage, a challenge inadequately mitigated by conventional post-hoc watermarking techniques that struggle to simultaneously ensure imperceptibility, functional correctness, and robustness. To overcome this limitation, the paper introduces the first embedded watermarking framework that natively integrates copyright information into the QCGM generation process. By leveraging a symmetric sampling strategy aligned with Gaussian priors and a latent-space synchronized drift correction mechanism, the proposed method achieves high-fidelity quantum circuit synthesis while enabling robust watermark embedding. Experimental results demonstrate that the approach maintains both high circuit fidelity and reliable watermark detection under various perturbations, offering a scalable copyright protection solution for AI-driven quantum design.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Adversarial Attacks & Robustness
• Knowledge Representation and Reasoning: Qualitative Reasoning

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Quantum cloud platforms have become the most widely adopted and mainstream approach for accessing quantum computing resources, due to the scarcity and operational complexity of quantum hardware. In this service-oriented paradigm, quantum circuits, which constitute high-value intellectual property, are exposed to risks of unauthorized access, reuse, and misuse. Digital watermarking has been explored as a promising mechanism for protecting quantum circuits by embedding ownership information for tracing and verification. However, driven by recent advances in generative artificial intelligence, the paradigm of quantum circuit design is shifting from individually and manually constructed circuits to automated synthesis based on quantum circuit generative models (QCGMs). In such generative settings, protecting only individual output circuits is insufficient, and existing post hoc, circuit-centric watermarking methods are not designed to integrate with the generative process, often failing to simultaneously ensure stealthiness, functional correctness, and robustness at scale. These limitations highlight the need for a new watermarking paradigm that is natively integrated with quantum circuit generative models. In this work, we present the first watermarking framework for QCGMs, which embeds ownership signals into the generation process while preserving circuit fidelity. We introduce a symmetric sampling strategy that aligns watermark encoding with the model's Gaussian prior, and a synchronization mechanism that counteracts adversarial watermark attack through latent drift correction. Empirical results confirm that our method achieves high-fidelity circuit generation and robust watermark detection across a range of perturbations, paving the way for scalable, secure copyright protection in AI-powered quantum design.

Problem

• quantum circuit generative models
• digital watermarking
• copyright protection
• generative AI
• quantum computing

Innovation

• quantum circuit generative models
• digital watermarking
• symmetric sampling
• latent drift correction
• AI-powered quantum design