Authorize-on-Demand: Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910041785761792 |
|---|---|
| author | Wang, Lianyu Wang, Meng Fu, Huazhu Zhang, Daoqiang |
| author_facet | Wang, Lianyu Wang, Meng Fu, Huazhu Zhang, Daoqiang |
| contents | The rapid adoption of vision-language models (VLMs) has heightened the demand for robust intellectual property (IP) protection of these high-value pretrained models. Effective IP protection should proactively confine model deployment within authorized domains and prevent unauthorized transfers. However, existing methods rely on static training-time definitions, limiting flexibility in dynamic environments and often producing opaque responses to unauthorized inputs. To address these limitations, we propose a novel dynamic authorization with legality-aware intellectual property protection (AoD-IP) for VLMs, a framework that supports authorize-on-demand and legality-aware assessment. AoD-IP introduces a lightweight dynamic authorization module that enables flexible, user-controlled authorization, allowing users to actively specify or switch authorized domains on demand at deployment time. This enables the model to adapt seamlessly as application scenarios evolve and provides substantially greater extensibility than existing static-domain approaches. In addition, AoD-IP incorporates a dual-path inference mechanism that jointly predicts input legality-aware and task-specific outputs. Comprehensive experimental results on multiple cross-domain benchmarks demonstrate that AoD-IP maintains strong authorized-domain performance and reliable unauthorized detection, while supporting user-controlled authorization for adaptive deployment in dynamic environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04896 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Authorize-on-Demand: Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMs Wang, Lianyu Wang, Meng Fu, Huazhu Zhang, Daoqiang Artificial Intelligence The rapid adoption of vision-language models (VLMs) has heightened the demand for robust intellectual property (IP) protection of these high-value pretrained models. Effective IP protection should proactively confine model deployment within authorized domains and prevent unauthorized transfers. However, existing methods rely on static training-time definitions, limiting flexibility in dynamic environments and often producing opaque responses to unauthorized inputs. To address these limitations, we propose a novel dynamic authorization with legality-aware intellectual property protection (AoD-IP) for VLMs, a framework that supports authorize-on-demand and legality-aware assessment. AoD-IP introduces a lightweight dynamic authorization module that enables flexible, user-controlled authorization, allowing users to actively specify or switch authorized domains on demand at deployment time. This enables the model to adapt seamlessly as application scenarios evolve and provides substantially greater extensibility than existing static-domain approaches. In addition, AoD-IP incorporates a dual-path inference mechanism that jointly predicts input legality-aware and task-specific outputs. Comprehensive experimental results on multiple cross-domain benchmarks demonstrate that AoD-IP maintains strong authorized-domain performance and reliable unauthorized detection, while supporting user-controlled authorization for adaptive deployment in dynamic environments. |
| title | Authorize-on-Demand: Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMs |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.04896 |