1330-GRM Context-Aware Privacy Detection in Vision-Language Models: Evaluating Input Strategies and Model Architectures
Year: 2026
Type: article
Abstract: Vision-Language Models (VLMs) support visual assistance by answering questions about images, but these images may contain sensitive information. The privacy risk depends on the image information and the user's question request. This study investigates question-dependent privacy detection and different input and prompting strategies. Preliminary experiments across four VLMs achieve 54%-84% accuracy. Initial question-based experiments show that question-only input achieves higher accuracy than direct image–question input. We evaluate structured and sequential privacy-aware processing to improve context-dependent privacy recognition.
Author: Joyee, Ramisa Fariha
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7237380810
FWCI:
Cites:
Cited by:
Related to:
