Problem
Research questions and friction points this paper is trying to address.
Personally Identifiable Information
Document Images
Redaction Risk
OCR Errors
Layout Structure
LeakageBench: Document-Level Leakage Risk for Redacting Personally Identifiable Information in Document Images
🤖 AI Summary
本文针对文档图像中个人身份信息（PII）泄露风险问题，通过构建LeakageBench基准数据集并评估多种检测方法来解决文档级PII去除不彻底的问题。
📝 Abstract
Real-world personally identifiable information (PII) redaction often operates on document images---scans, screenshots, and PDF renderings---where OCR errors, layout structure, and visual noise determine whether sensitive information is actually removed. Existing PII benchmarks are mostly text-centric and do not measure document-level redaction risk: a page remains unsafe if even one identifier is missed. We introduce LeakageBench, a challenge set of 500 document images with 11,954 GDPR-aligned PII annotations spanning direct identifiers, linkage keys, and contextual re-identification surfaces. We evaluate generic OCR pipelines, commercial and task-adapted OCR-dependent detectors, and OCR-free vision-language models using entity-level F1, group-wise leakage, and document-level leakage metrics. Code Interpreter raises GPT-5.5 localization F1 from 0.090 to 0.249, but critical page-level leakage remains 0.968. These results show that stronger detection and tool assistance improve localization without making most pages safe for release. LeakageBench provides a diagnostic benchmark for high-recall, spatially grounded PII redaction in document images.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Document-Level Redaction
PII Detection
OCR Errors
Layout Structure
Visual Noise
🔎 Similar Papers
No similar papers found.
