Technical
Deep dives into PII detection, NER, and anonymization technology
33 articles
Cross-Platform PII: Mac, Linux, and Windows
Privacy officers on Mac, legal on Windows, data engineers on Linux — all processing the same data with different tools. Here's why OS-agnostic detection.
Cross-Application PII: Word, Chrome, and AI
Customer data flows from browser research to Word drafts to Claude prompts. Each context switch is a potential leakage point.
GDPR in App Logs: JSON PII Compliance
Application logs contain customer email addresses, IPs, and account numbers that GDPR Article 5(1)(e) requires be managed.
GDPR Log Anonymization: Keep Debugging
Application logs silently accumulate user emails, IPs, and account numbers. Here's how to share logs with third parties, contractors, and observability.
Document Format Fragmentation in PII Tools
A single DSAR response may span Word contracts, PDF invoices, Excel customer lists, and CSV exports. Using different tools for each format creates.
Why Binary PII Detection Fails Compliance
Detected/not-detected is insufficient for compliance contexts that require human judgment. Here's why confidence scoring transforms PII anonymization from.
Presidio: 3-Week Setup vs Managed PII
Microsoft Presidio has thousands of GitHub stars and hundreds of open issues. Setup complexity, PySpark integration overhead, and Python dependency.
6 Weeks to 3 Days: Managed PII Setup
Healthcare SaaS teams spend 6 weeks on self-hosted Presidio production deployment before switching to managed API. The managed API replaces the deployment.
Free PII Detection Costs €13K/Year
Self-hosting Presidio requires 40-80 hours initial setup and 5-10 hours/month ongoing maintenance. At €100/hour engineering rates, that's €13,200+.
Presidio 22.7% Precision Problem
A 2024 benchmark found Presidio's person name recognizer achieves 22.7% precision in business documents — meaning 77.3% of detections are false positives.
Reproducible Privacy: ML Presets
ML training data anonymization must be consistent and reproducible. If data scientists A and B apply different entity types, training datasets are.
GDPR Pipeline: Anonymize Before Storage
dbt column tags are not GDPR compliance. Raw customer data hits your Snowflake warehouse unmasked before tag-based policies apply.
FOIA: Redaction from Weeks to Hours
The federal government spent an estimated $500M on FOIA processing in 2024, mostly manual redaction. ARPA-H explicitly sought AI redaction software to.
GDPR ML Training Data Anonymization
GDPR restricts using personal data for ML training beyond its original collection purpose. Data scientists relying on ad-hoc Python scripts create.
FOIA: 80% Faster with Batch Redaction
US federal agencies received 1.5 million FOIA requests in FY2024 at an average cost of $482 per request. Batch PII redaction reduces processing time from.
Presidio vs anonym.legal: Build vs Buy
Microsoft Presidio is technically free but costs 40-80 engineering hours to deploy properly. anonym.legal delivers the same ML accuracy as a managed SaaS.
Air-Gapped Privacy: Anonymize Offline
FedRAMP and ITAR environments have one thing in common — the cloud is not an option. Reversible pseudonymization under GDPR Art.
The False Positive Tax on PII Tools
Presidio GitHub issue #1071 documents systematic false positives. A 2024 study found 22.7% precision in mixed-language enterprise datasets.
Arabic & Hebrew PII: Western Tools Fail
GDPR doesn't end at the Bosphorus. Arabic and Hebrew PII in EU business workflows is systematically unprotected. XLM-RoBERTa cross-lingual detection and.
Mixed-Language PII: Monolingual Tools Fail
72% of EU enterprises process documents in 3+ languages simultaneously. Mixed-language documents cause 45% higher PII miss rates in monolingual NER tools.
APAC PII: Thai, Indonesian, Vietnamese
A Singapore fintech processing 500,000 monthly support chats across 12 APAC languages found their English-only tool missed PII in 60% of non-English.
False Positives: Why ML Redaction Fails
A 2024 benchmark found Presidio generated 13,536 false positive name detections across 4,434 samples — flagging pronouns, vessel names, and countries as.
ISO 27001 + ZK Cuts Vendor Assessment Time
A 2025 survey found 'lack of recognized security certification' was the #2 reason CISOs disqualify SaaS vendors. Here's what the ISO 27001 +.
ZK Architecture Shortens Sales Cycles
Enterprise vendor security questionnaires average 100+ questions. Zero-knowledge architecture answers the hardest ones definitively — and converts.
LastPass Breach: Vendor Security Lessons
LastPass encrypted their users' data. The vaults were still exfiltrated. 600K+ Okta records followed. SaaS security incidents increased 300% from 2022 to.
Evaluating ZK Claims After LastPass
$438M stolen from LastPass users after their 'encrypted' vaults were breached. A £1.2M ICO fine followed. Here's the checklist for evaluating whether a.
LangChain CVE-2025-68664: How PII Leaks Through Your RAG Pipeline
CVSS 9.3. LangChain's serialization functions expose environment variables and secrets to attacker-controlled LLMs. How to detect and fix PII leaks.
LibreOffice PII Anonymization Extension
Step-by-step guide to anonymizing PII in LibreOffice documents using the anonym.legal extension.
LibreOffice vs Office: PII Redaction
Detailed comparison of PII anonymization capabilities in LibreOffice (anonym.legal extension) vs. Microsoft Office (Office Add-in).
Air-Gapped PII: Offline-First for Defense
41% of enterprise security policies prohibit cloud processing of classified documents.
Reversible vs Permanent Redaction Choice
GDPR distinguishes anonymization from pseudonymization. Courts need originals. Research needs re-identification. Learn when to use each approach.
Multi-Language NER: English Fails Arabic
English NER models achieve 85-92% accuracy. Arabic and Chinese? Often 50-70%. Learn about the technical challenges and how to build truly.
Use Claude & ChatGPT Without Leaking PII
A developer's guide to using AI assistants securely. Set up MCP Server integration for transparent PII protection in Claude Desktop, Cursor, and VS Code.
Start Protecting Your Data Today
285+ entity types, 48 languages, enterprise-grade security at startup pricing.
About this page
We update this page when our platform or the law changes.
Read our founder note for how we work.
Each change shows up in the timestamp at the top.
Related reading
- Common questions
- Glossary
- How tokens work
- Security posture
- Where we comply
- What we detect
- Case studies
- Release notes
We follow these rules
- GDPR (EU 2016/679).
- ISO/IEC 27001:2022.
- NIS2 (EU 2022/2555).
- HIPAA safe harbor under 45 CFR § 164.514(b)(2).
Our promise
We do not sell your data.
We do not train models on your text.
We store your files in Germany.
You can delete your account at any time.
You own your work.
Where we run
Our servers live in Falkenstein, Germany.
We use Hetzner. They hold ISO 27001 certification.
All data stays in the EU.
Backups run every day.
Need help?
Email support@anonym.legal.
We reply within one business day.
How we test
We run a full check suite on every release.
Each surface gets its own sweep script and report.
Human reviewers spot-check the output each week.
We track recall and precision on a labelled set.
Bad runs block the deploy.
What we never do
- We never sell your information to third parties.
- We never train models on what you upload.
- We never keep your work after you delete it.
- We never share keys with any outside firm.
- We never run ads inside the product.
Plans in plain words
We sell credits, not seats.
One credit covers one short job.
Long jobs use a few credits each.
You can top up at any time.
Unused credits roll over each month.
Read the plans page for current rates.
Who built this
A small team of engineers and lawyers built this.
We ship from Europe and work in the open.
Our founder note spells out why we started.
Where to start
- Open the web app and try a sample file.
- Learn how credits get counted.
- See current plans and limits.
- Meet the team behind the product.
How the parts fit
A browser add-on cleans text inside Chrome.
A Word plug-in handles drafts in Office.
A small desktop tool works on whole folders.
An agent protocol link feeds large models safely.
All four share one core engine and one rule set.
Words from our team
We started this work after a lunch about cookies.
One friend kept getting odd ads on her phone.
We asked why a court file leaked through a draft.
We sketched the first build on a napkin that week.
By month three we had a tiny demo for a friend.
She used it on her first case the next day.
Common questions we hear
Can the tool read scanned PDFs? Yes, with OCR.
Does it work on long files? Yes, in small chunks.
Can I roll my own rule set? Yes, save it as a preset.
Does it run offline? The desktop build runs offline.
Do you keep my files? No, the cloud build wipes after each run.
Will it learn from my work? No, we never train on inputs.
A short tour of the workflow
Upload a file or paste a snippet of prose.
Pick the entities you want gone from the draft.
Choose a method: replace, mask, hash, encrypt, or redact.
Press run and watch the side panel show each hit.
Skim the result and tweak any rule that misfired.
Save the cleaned file or send it to a teammate.