Visual Redaction — Privacy Privacy model, limits, and safety notes for Visual Redaction. Open tool · How-to · Privacy Visual Redaction privacy model This tool is classified as heavy workload and runs in On-device mode. Current status: beta (fully-functional). Release note: Visual redaction burns black rectangles into rasterized pages. All pages are flattened for uniformity. What this does Applies the selected transformation to the document or exported output. Keeps processing local in browser when marked On-device. Uses monthly local counters for usage quotas. What this does not protect It does not remove names or sensitive content visible in document text or images. It does not guarantee legal anonymity or endpoint compromise protection. For hybrid tools, privacy depends on explicit cloud opt-in when enabled. Redaction is irreversible by design. There is no undo after burning. The original text under redacted areas is destroyed, not hidden. Output file size increases significantly because every page becomes a raster image. Expect 0.5-1.5MB per page at 200 DPI. Text in the output PDF is not selectable. If recipients need searchable text, they would need to OCR the result. Documents over 200 pages are capped for browser memory safety. Split first, then redact sections individually. This is visual redaction only. It does not produce PDF redaction annotations compatible with Adobe's redaction workflow. Safe workflow defaults Verify output manually before sharing. Use security guidance at /security for higher-risk scenarios. Keep original and transformed files separated to avoid accidental leaks.