SOURCE-LINKED INTELLIGENCE

LeakageBench: Document-Level Leakage Risk for Redacting Personally Identifiable Information in Document Images

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

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.

Read original source ↗ Open in workspace

recordType

paper

region

Global