mlsanityData to 7 Oct 2026

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

arXiv 2601.09449 ↗First posted 14 Jan 2026cs.CVcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 24 references that are in the map. First posted on arXiv 14 Jan 2026.

Builds on

19 of 24 references.

References · 19

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Concept Bottleneck Modelscited by 1,022
  3. 2022Visual Classification via Description from Large Language Modelscited by 331
  4. 2022Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classificationcited by 310
  5. 2022Post-hoc Concept Bottleneck Modelscited by 289
  6. 2023Label-Free Concept Bottleneck Modelscited by 282
  7. 2017Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Imagescited by 101
  8. 2024Pre-trained Vision-Language Models Learn Discoverable Visual Conceptscited by 16
  9. 2024Privacy-Aware Visual Language Modelscited by 12
  10. 2024Rethinking VLMs and LLMs for Image Classificationcited by 12
  11. 2024Data Privacy Vocabulary (DPV) -- Version 2cited by 7
  12. 2025Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Modelscited by 6
7 more
  1. 2025MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Modelscited by 5
  2. 2023Human-interpretable and deep features for image privacy classificationcited by 4
  3. 2024Image-guided topic modeling for interpretable privacy classificationcited by 4
  4. 2025EgoPrivacy: What Your First-Person Camera Says About You?cited by 4
  5. 2024Explaining models relating objects and privacycited by 3
  6. 2023PEAK: Explainable Privacy Assistant through Automated Knowledge Extractioncited by 2
  7. 2025On the Robustness of Vision-Language Models in Zero-shot Privacy Classificationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Private Attribute Inference from Images with Vision-Language Models
  2. 2026Which private attributes do VLMs agree on and predict well?
  3. 2026Assessing Privacy Preservation and Utility in Online Vision-Language Models
  4. 2026Vision Language Model Helps Private Information De-Identification in Vision Data
  5. 2024The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Models
  6. 2026Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs
  7. 2026See No Evil: Semantic Context-Aware Privacy Risk Detection for AR
  8. 2025The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework