Authorize-on-Demand: Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMs

2026-03-05

AI Summary

This work addresses the limitations of existing static authorization mechanisms in vision-language models (VLMs), which struggle to adapt to dynamic deployment scenarios and lack transparent responses to unauthorized inputs. To overcome these challenges, the authors propose a lightweight, legality-aware dynamic authorization framework that integrates a dual-path reasoning mechanism. This approach simultaneously produces task-specific outputs and assesses input legitimacy, enabling users to specify or switch authorized domains on demand during deployment. By moving beyond conventional static authorization paradigms, the method demonstrates strong performance across multiple cross-domain benchmarks, effectively detecting unauthorized usage while preserving model efficacy within authorized domains. The framework significantly enhances the adaptability and scalability of VLMs in dynamic environments without compromising responsiveness or transparency.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Authentication, authorization, and access control

Abstract

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.

Problem

• intellectual property protection
• dynamic authorization
• vision-language models
• authorized domains
• unauthorized transfer

Innovation

• dynamic authorization
• legality-aware
• intellectual property protection
• vision-language models
• authorize-on-demand