PrivLEX: Detecting legal concepts in images through Vision-Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Baranouskaya, Darya, Cavallaro, Andrea
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909990339477504
author Baranouskaya, Darya
Cavallaro, Andrea
author_facet Baranouskaya, Darya
Cavallaro, Andrea
contents We present PrivLEX, a novel image privacy classifier that grounds its decisions in legally defined personal data concepts. PrivLEX is the first interpretable privacy classifier aligned with legal concepts that leverages the recognition capabilities of Vision-Language Models (VLMs). PrivLEX relies on zero-shot VLM concept detection to provide interpretable classification through a label-free Concept Bottleneck Model, without requiring explicit concept labels during training. We demonstrate PrivLEX's ability to identify personal data concepts that are present in images. We further analyse the sensitivity of such concepts as perceived by human annotators of image privacy datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2601_09449
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PrivLEX: Detecting legal concepts in images through Vision-Language Models
Baranouskaya, Darya
Cavallaro, Andrea
Computer Vision and Pattern Recognition
We present PrivLEX, a novel image privacy classifier that grounds its decisions in legally defined personal data concepts. PrivLEX is the first interpretable privacy classifier aligned with legal concepts that leverages the recognition capabilities of Vision-Language Models (VLMs). PrivLEX relies on zero-shot VLM concept detection to provide interpretable classification through a label-free Concept Bottleneck Model, without requiring explicit concept labels during training. We demonstrate PrivLEX's ability to identify personal data concepts that are present in images. We further analyse the sensitivity of such concepts as perceived by human annotators of image privacy datasets.
title PrivLEX: Detecting legal concepts in images through Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.09449