Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Feiran, Zhang, Yuzhe, Huang, Xinyi, Peng, Yinan, Li, Xinfeng, Wang, Lixu, Shen, Yutong, Duan, Ranjie, Qin, Simeng, Jia, Xiaojun, Wen, Qingsong, Dong, Wei
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.19139
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909622399401984
author Liu, Feiran
Zhang, Yuzhe
Huang, Xinyi
Peng, Yinan
Li, Xinfeng
Wang, Lixu
Shen, Yutong
Duan, Ranjie
Qin, Simeng
Jia, Xiaojun
Wen, Qingsong
Dong, Wei
author_facet Liu, Feiran
Zhang, Yuzhe
Huang, Xinyi
Peng, Yinan
Li, Xinfeng
Wang, Lixu
Shen, Yutong
Duan, Ranjie
Qin, Simeng
Jia, Xiaojun
Wen, Qingsong
Dong, Wei
contents Our research reveals a new privacy risk associated with the vision-language model (VLM) agentic framework: the ability to infer sensitive attributes (e.g., age and health information) and even abstract ones (e.g., personality and social traits) from a set of personal images, which we term "image private attribute profiling." This threat is particularly severe given that modern apps can easily access users' photo albums, and inference from image sets enables models to exploit inter-image relations for more sophisticated profiling. However, two main challenges hinder our understanding of how well VLMs can profile an individual from a few personal photos: (1) the lack of benchmark datasets with multi-image annotations for private attributes, and (2) the limited ability of current multimodal large language models (MLLMs) to infer abstract attributes from large image collections. In this work, we construct PAPI, the largest dataset for studying private attribute profiling in personal images, comprising 2,510 images from 251 individuals with 3,012 annotated privacy attributes. We also propose HolmesEye, a hybrid agentic framework that combines VLMs and LLMs to enhance privacy inference. HolmesEye uses VLMs to extract both intra-image and inter-image information and LLMs to guide the inference process as well as consolidate the results through forensic analysis, overcoming existing limitations in long-context visual reasoning. Experiments reveal that HolmesEye achieves a 10.8% improvement in average accuracy over state-of-the-art baselines and surpasses human-level performance by 15.0% in predicting abstract attributes. This work highlights the urgency of addressing privacy risks in image-based profiling and offers both a new dataset and an advanced framework to guide future research in this area.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19139
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework
Liu, Feiran
Zhang, Yuzhe
Huang, Xinyi
Peng, Yinan
Li, Xinfeng
Wang, Lixu
Shen, Yutong
Duan, Ranjie
Qin, Simeng
Jia, Xiaojun
Wen, Qingsong
Dong, Wei
Computer Vision and Pattern Recognition
Our research reveals a new privacy risk associated with the vision-language model (VLM) agentic framework: the ability to infer sensitive attributes (e.g., age and health information) and even abstract ones (e.g., personality and social traits) from a set of personal images, which we term "image private attribute profiling." This threat is particularly severe given that modern apps can easily access users' photo albums, and inference from image sets enables models to exploit inter-image relations for more sophisticated profiling. However, two main challenges hinder our understanding of how well VLMs can profile an individual from a few personal photos: (1) the lack of benchmark datasets with multi-image annotations for private attributes, and (2) the limited ability of current multimodal large language models (MLLMs) to infer abstract attributes from large image collections. In this work, we construct PAPI, the largest dataset for studying private attribute profiling in personal images, comprising 2,510 images from 251 individuals with 3,012 annotated privacy attributes. We also propose HolmesEye, a hybrid agentic framework that combines VLMs and LLMs to enhance privacy inference. HolmesEye uses VLMs to extract both intra-image and inter-image information and LLMs to guide the inference process as well as consolidate the results through forensic analysis, overcoming existing limitations in long-context visual reasoning. Experiments reveal that HolmesEye achieves a 10.8% improvement in average accuracy over state-of-the-art baselines and surpasses human-level performance by 15.0% in predicting abstract attributes. This work highlights the urgency of addressing privacy risks in image-based profiling and offers both a new dataset and an advanced framework to guide future research in this area.
title The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.19139