Registration prompt copyright verification method and device based on multi-model joint gradient optimization
By generating adversarial hints through multi-model joint gradient optimization, the robustness of copyright verification for large language models is insufficient, achieving stable copyright verification across models, avoiding performance degradation, and applicable to copyright protection of multiple homologous models.
Patent Information
- Application Number
- CN202510474773.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-16
- Publication Date
- 2026-07-03
AI Technical Summary
Existing copyright verification techniques for large language models lack robustness, especially single-model fingerprint watermark generation, which is weak in adversarial capabilities and has poor transferability, making it difficult to effectively cover diverse variations of the same series of models. Furthermore, traditional methods may impair model performance or be easily tampered with.
We employ a multi-model joint gradient optimization approach, which constructs a multi-model ensemble through adversarial suffix generation and optimization. This generates consistent and effective adversarial hints across multiple homologous models, avoiding reliance on model fine-tuning and enhancing the cross-model adaptability and robustness of fingerprints.
It significantly improves the robustness and stability of copyright verification, effectively identifies copyrights for various model series, avoids performance degradation, is suitable for protecting open-source models from leakage and unauthorized distribution, and has broad practical application value.