Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Vision Language Model Helps Private Information De-Identification in Vision Data

About

Visual Language Models (VLMs) have gained significant popularity due to their remarkable ability. While various methods exist to enhance privacy in text-based applications, privacy risks associated with visual inputs remain largely overlooked such as Protected Health Information (PHI) in medical images. To tackle this problem, two key tasks: accurately localizing sensitive text and processing it to ensure privacy protection should be performed. To address this issue, we introduce VisShield (Vision Privacy Shield), an end-to-end framework designed to enhance the privacy awareness of VLMs. Our framework consists of two key components: a specialized instruction-tuning dataset OPTIC (Optical Privacy Text Instruction Collection) and a tailored training methodology. The dataset provides diverse privacy-oriented prompts that guide VLMs to perform targeted Optical Character Recognition (OCR) for precise localization of sensitive text, while the training strategy ensures effective adaptation of VLMs to privacy-preserving tasks. Specifically, our approach ensures that VLMs recognize privacy-sensitive text and output precise bounding boxes for detected entities, allowing for effective masking of sensitive information. Extensive experiments demonstrate that our framework significantly outperforms existing approaches in handling private information, paving the way for privacy-preserving applications in vision-language models. Our dataset and code can be found here.

Tiejin Chen, Pingzhi Li, Kaixiong Zhou, Tianlong Chen, Hua Wei• 2026

Related benchmarks

TaskDatasetResultRank
De-identificationBase Image Dataset (train)
Name IoU91.94
3
De-identificationCOCO
Name IoU90.75
3
De-identificationADE-20K
Name IoU90.75
3
De-identificationRITE
Name IoU97.23
3
De-identificationBase Image Dataset Generated (Evaluation Set)
Name Accuracy94.78
2
De-identificationCOCO Generated (Evaluation Set)
Name Accuracy94.7
2
De-identificationADE-20K Generated (test)
Name De-identification Accuracy91.96
2
De-identificationRITE Generated (Evaluation Set)
Accuracy (Name)93.94
2
Object Detectionreal-world dataset Phone Number 2018 (test)
mAP54.39
2
Object Detectionreal-world 2018 (test)
mAP60.37
2
Showing 10 of 10 rows

Other info

Follow for update