anonym.legal

By · Last updated 2026-05-28

All Comparisons
Enterprise NLP vs. Regex

anonym.legal vs Caviard.ai

Caviard.ai is a Chrome extension that uses regex patterns for PII detection, achieving 60–75% recall with 15–30% false positive rates — insufficient for regulated compliance work. anonym.legal’s 3-layer NLP engine delivers 92–98% recall across 48 languages with deterministic, auditable results on web, desktop, Office Add-in, and all browsers.

Start Free TrialView Pricing

Learn more about Caviard.ai

Feature Comparison

Featureanonym.legalCaviard.ai
Detection TechnologyYesRegex patterns only
Entity Types285+~30–50 patterns
Language Support48 languagesLimited (regex gaps on non-ASCII)
Platform SupportYesChrome extension only
Per-Entity Confidence ScoringYesNo
Deterministic ResultsYesPattern-based only
Recall RateYes60–75%
False Positive RateYes15–30%
ISO 27001YesNot documented
Compliance Audit TrailYesNo
Reversible EncryptionAES-256-GCMNo (local browser processing)
Office Add-inYesNo
PricingFree to €29/moNot published

Comparison based on publicly available information. "Not found" indicates feature not documented on product page. Last updated February 2026.

Why Choose anonym.legal

All Browsers + Desktop — Not Chrome-Only

anonym.legal works in Chrome, Firefox, Edge, Safari, and as a desktop app. Caviard.ai is a Chrome extension — staff using other browsers get no protection.

Deterministic NLP vs. Regex Patterns

anonym.legal uses 3-layer NLP (Presidio + spaCy + XLM-RoBERTa transformers). Regex cannot understand context: it misses location entities, confuses company names with text, and fails on all non-ASCII scripts.

ISO 27001 Certified Infrastructure

anonym.legal runs on Hetzner Germany with ISO 27001 certification. Caviard.ai has no documented security certifications.

48 Languages vs. Regex Gaps

Regex-based detection fails on German umlauts, Arabic, Chinese, Hebrew, and other non-ASCII characters. anonym.legal’s multilingual NLP covers 48 languages natively.

Per-Entity Confidence Scoring

Every detection includes a 0–100% confidence score and the rule/model that triggered it — required for legal defensibility and HIPAA audit trails. Caviard.ai provides no confidence scoring.

285+ Entity Types

Country-specific IDs with checksum validation, 48-language NER, medical record numbers, financial identifiers. Caviard.ai covers ~30–50 regex patterns.

When anonym.legal is the right choice

anonym.legal outperforms Caviard.ai when:

  • You need compliance-grade recall (92–98%) rather than basic pattern matching (60–75%)
  • Your team uses Firefox, Edge, Safari, or desktop applications — not only Chrome
  • You process multilingual content: German, French, Arabic, Chinese, Hebrew, or any of 48 languages
  • You require per-entity confidence scores and audit trails for HIPAA, GDPR, or e-discovery
  • You need reversible anonymization — decrypt placeholders when required by law

Frequently Asked Questions

What is the difference between regex-based and NLP-based PII detection?

Regex patterns match fixed text structures (e.g., SSN format). They miss context-dependent PII: names in sentences, location entities, and any pattern that varies slightly. NLP models understand language context — anonym.legal’s 3-layer pipeline (Presidio + spaCy + XLM-RoBERTa) achieves 92–98% recall vs. 60–75% for regex-only tools like Caviard.ai.

Does Caviard.ai work in Firefox, Edge, or Safari?

No. Caviard.ai is a Chrome extension and only works in Chrome-based browsers. anonym.legal works in all major browsers via the web app, provides dedicated Chrome and Edge extensions, and includes a standalone Desktop App for Windows, macOS, and Linux.

What security certifications does Caviard.ai have?

Caviard.ai does not publish ISO 27001 or SOC 2 certifications. anonym.legal runs on Hetzner Germany infrastructure with ISO 27001 certification, GDPR-compliant data processing agreements, and zero-knowledge authentication verified by independent security audit.

How does anonym.legal handle multilingual PII that Caviard.ai misses?

Regex patterns fail on non-ASCII characters: German umlauts (ä, ö, ü), Arabic script, Chinese characters, Hebrew letters. anonym.legal’s NLP models are trained on 48 languages and handle character normalization, Unicode boundaries, and language-specific ID formats (German Personalausweis, French NIR, Arabic national IDs, etc.).

What false positive rates can I expect?

Caviard.ai’s regex approach produces 15–30% false positive rates — flagging non-PII text as sensitive. This creates unnecessary redaction of legitimate content. anonym.legal’s NLP pipeline reduces false positives to under 5% through contextual understanding, confidence scoring thresholds, and per-entity override controls.

Does anonym.legal provide audit trails for compliance?

Yes. Every detection includes the entity type, confidence score, detection method (rule ID or model name), and timestamp — creating a defensible audit trail for HIPAA, GDPR, and e-discovery requirements. Caviard.ai does not provide per-detection audit trails.

Enterprise NLP PII Detection

92–98% recall. 48 languages. All browsers + Desktop. ISO 27001. Free to start.

Start Free TrialView More Comparisons

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

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

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.