Authorize-on-Demand: Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMs
This work provides a more flexible and user-controlled IP protection mechanism for VLM developers and deployers, addressing the limitations of static authorization in dynamic application environments.
This paper addresses the need for dynamic intellectual property (IP) protection in vision-language models (VLMs) by proposing Authorize-on-Demand (AoD-IP), a framework that allows users to specify authorized domains at deployment time. AoD-IP maintains strong performance in authorized domains and reliably detects unauthorized usage, offering greater adaptability than static methods.
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.