按需授权：面向视觉语言模型的动态授权与合法性感知知识产权保护
Authorize-on-Demand: Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMs
为 VLM 部署提供可动态切换的授权域机制与合法性判别分支，视觉研究者可借鉴其双路径推理设计，在保持授权域任务性能的同时检测越界输入，用于模型分发与滥用防护。
原文依据 AoD-IP incorporates a dual-path inference mechanism that jointly predicts input legality-aware and task-specific outputs.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视觉语言模型（VLM）的快速普及，提升了对这类高价值预训练模型进行稳健知识产权（IP）保护的需求。有效的知识产权保护应主动将模型部署限制在授权域内，并阻止未经授权的迁移。然而，现有方法依赖训练时静态定义的授权域，限制了其在动态环境中的灵活性，且对未授权输入往往给出不透明的响应。为解决这些局限，我们提出一种面向 VLM 的新型动态授权与合法性感知知识产权保护框架（AoD-IP），该框架支持按需授权与合法性感知评估。AoD-IP 引入一个轻量级动态授权模块，实现灵活、用户可控的授权，使用户能够在部署时按需主动指定或切换授权域。这使模型能够随应用场景演进而无缝适配，并相比现有静态域方法提供显著更强的可扩展性。此外，AoD-IP 采用双路径推理机制，联合预测输入的合法性感知结果与任务特定输出。在多个跨域基准上的综合实验结果表明，AoD-IP 在保持较强授权域性能与可靠未授权检测的同时，支持用户可控授权，从而适应动态环境中的自适应部署。
英文原文摘要 1472 字符
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.