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

arXiv: https://arxiv.org/abs/2601.09449 · HTML: https://mlsanity.com/paper/2601.09449/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 24 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Visual Classification via Description from Large Language Models](https://mlsanity.com/paper/2210.07183/) (2022)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Label-Free Concept Bottleneck Models](https://mlsanity.com/paper/2304.06129/) (2023)
- [Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images](https://mlsanity.com/paper/1703.10660/) (2017)
- [Pre-trained Vision-Language Models Learn Discoverable Visual Concepts](https://mlsanity.com/paper/2404.12652/) (2024)
- [Privacy-Aware Visual Language Models](https://mlsanity.com/paper/2405.17423/) (2024)
- [Rethinking VLMs and LLMs for Image Classification](https://mlsanity.com/paper/2410.14690/) (2024)
- [Data Privacy Vocabulary (DPV) -- Version 2](https://mlsanity.com/paper/2404.13426/) (2024)
- [Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Models](https://mlsanity.com/paper/2509.23827/) (2025)
- [MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models](https://mlsanity.com/paper/2511.16940/) (2025)
- [Human-interpretable and deep features for image privacy classification](https://mlsanity.com/paper/2310.19582/) (2023)
- [Image-guided topic modeling for interpretable privacy classification](https://mlsanity.com/paper/2409.18674/) (2024)
- [EgoPrivacy: What Your First-Person Camera Says About You?](https://mlsanity.com/paper/2506.12258/) (2025)
- [Explaining models relating objects and privacy](https://mlsanity.com/paper/2405.01646/) (2024)
- [PEAK: Explainable Privacy Assistant through Automated Knowledge Extraction](https://mlsanity.com/paper/2301.02079/) (2023)
- [On the Robustness of Vision-Language Models in Zero-shot Privacy Classification](https://mlsanity.com/paper/2510.09253/) (2025)

## Abstract (arXiv)

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.