Evaluating the Efficacy of Large Language Models for Generating Fine-Grained Visual Privacy Policies in Homes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Shuning, Ma, Ying, Yi, Xin, Li, Hewu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912514944532480
author Zhang, Shuning
Ma, Ying
Yi, Xin
Li, Hewu
author_facet Zhang, Shuning
Ma, Ying
Yi, Xin
Li, Hewu
contents The proliferation of visual sensors in smart home environments, particularly through wearable devices like smart glasses, introduces profound privacy challenges. Existing privacy controls are often static and coarse-grained, failing to accommodate the dynamic and socially nuanced nature of home environments. This paper investigates the viability of using Large Language Models (LLMs) as the core of a dynamic and adaptive privacy policy engine. We propose a conceptual framework where visual data is classified using a multi-dimensional schema that considers data sensitivity, spatial context, and social presence. An LLM then reasons over this contextual information to enforce fine-grained privacy rules, such as selective object obfuscation, in real-time. Through a comparative evaluation of state-of-the-art Vision Language Models (including GPT-4o and the Qwen-VL series) in simulated home settings , our findings show the feasibility of this approach. The LLM-based engine achieved a top machine-evaluated appropriateness score of 3.99 out of 5, and the policies generated by the models received a top human-evaluated score of 4.00 out of 5.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00321
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating the Efficacy of Large Language Models for Generating Fine-Grained Visual Privacy Policies in Homes
Zhang, Shuning
Ma, Ying
Yi, Xin
Li, Hewu
Human-Computer Interaction
The proliferation of visual sensors in smart home environments, particularly through wearable devices like smart glasses, introduces profound privacy challenges. Existing privacy controls are often static and coarse-grained, failing to accommodate the dynamic and socially nuanced nature of home environments. This paper investigates the viability of using Large Language Models (LLMs) as the core of a dynamic and adaptive privacy policy engine. We propose a conceptual framework where visual data is classified using a multi-dimensional schema that considers data sensitivity, spatial context, and social presence. An LLM then reasons over this contextual information to enforce fine-grained privacy rules, such as selective object obfuscation, in real-time. Through a comparative evaluation of state-of-the-art Vision Language Models (including GPT-4o and the Qwen-VL series) in simulated home settings , our findings show the feasibility of this approach. The LLM-based engine achieved a top machine-evaluated appropriateness score of 3.99 out of 5, and the policies generated by the models received a top human-evaluated score of 4.00 out of 5.
title Evaluating the Efficacy of Large Language Models for Generating Fine-Grained Visual Privacy Policies in Homes
topic Human-Computer Interaction
url https://arxiv.org/abs/2508.00321