How Does PII Detection Work?
PII detection identifies personal data in text using pattern matching and machine learning. anonym.legal uses a hybrid approach:
- 1Pattern Matching: Regex patterns detect structured data (SSNs, credit cards, IBANs) with checksum validation.
- 2Named Entity Recognition: NER models identify names, locations, and organizations in 48 languages.
- 3Context Scoring: Each detection is scored based on surrounding context to minimize false positives.
This hybrid approach detects 285+ entity types while maintaining deterministic, reproducible results — essential for compliance and legal discovery.
なぜAIではなく正規表現なのか？
私たちのアプローチ
- 100%再現可能な結果
- コンプライアンスのための完全な監査可能性
- トレーニングデータは不要
- 透明な意思決定
- 迅速で予測可能なパフォーマンス
- 時間の経過によるモデルの漂流なし
AI/MLアプローチ
- 実行間で結果が異なる
- ブラックボックスの意思決定
- トレーニングデータが必要
- 監査が難しい
- 高い計算コスト
- 時間の経過によるモデルの漂流
10ステッププロセス
入力から出力まで、あなたの文書に何が起こるかを正確に示します
テキストの入力
ウェブインターフェース、API、またはOfficeアドインを介して文書を提出します
言語検出
システムが最適な処理のために文書の言語を特定します
トークン化
テキストがパターンマッチングのためにトークンに分割されます
パターンマッチング
正規表現パターンが50以上のエンティティタイプをスキャンします
コンテキスト分析
周囲のテキストが検出精度を向上させます
信頼度スコアリング
各検出に信頼度スコアが付与されます
エンティティ分類
検出された項目はタイプ別に分類されます
結果のレビュー
位置とスコアを持つすべての検出を確認します
匿名化の適用
方法を選択します：置換、削除、ハッシュ、暗号化、またはマスク
出力文書
匿名化された文書をダウンロードします
MCPサーバー：プライバシー優先のAI統合
あなたのデータがMCPサーバーを通じて流れる方法、AIツールを安全に保つために
AIツールリクエスト
あなたのAIツール（Cursor、Claude）がPIIを含むリクエストを送信します
MCPサーバーが傍受
サーバーがすべてのPIIエンティティを分析し検出します
匿名化
PIIがトークンに置き換えられるか、削除されます
AI処理
AIは匿名化されたデータのみを受け取り処理します
レスポンスの返却
AIのレスポンスがMCPサーバーを通じて返されます
デトークン化
オプション：元の値がユーザーに復元されます
実世界の例
John Doeの支払いを処理、メールjohn@example.com、カード4532-1111-2222-3333AIが見るもの
PII_PERSON_001の支払いを処理、メールPII_EMAIL_001、カードPII_CREDIT_CARD_001あなたが受け取るもの
Frequently Asked Questions
Why use regex instead of AI for PII detection?
Regex-based detection is deterministic and reproducible. The same input always produces the same output. AI/ML models can be unpredictable and may miss or falsely flag data. For compliance, reproducibility matters.
How accurate is the detection?
Our hybrid approach combines regex patterns with Named Entity Recognition (NER) for high accuracy. All patterns include checksum validation where applicable (credit cards, IBANs, SSNs). False positives are minimized through context-aware scoring.
What happens to my data during processing?
Text is sent to our EU-hosted servers (Hetzner, Germany) over TLS 1.3 for analysis. We don't store your data after processing. With Zero-Knowledge auth, we can't even identify which user made the request.
Can I add custom entity types?
Yes! You can create custom recognizers with your own regex patterns and context words. Custom entities support the same operators (replace, mask, hash, encrypt, redact) as built-in types.
How does reversible encryption work?
The Encrypt operator uses AES-256-GCM encryption with your key. Only you can decrypt. This allows re-identification for audits or legal discovery while keeping data protected in transit and storage.
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.