By George Curta · Last updated 2026-06-15
anonym.legal vs Redact PDF AI
Redact PDF AI nahrá vaše dokumenty do Microsoft Azure na spracovanie — čo znamená, že ich servery môžu čítať vaše nešifrované súbory. anonym.legal používa šifrovaní AES-256-GCM na strane klienta pred odoslaním: vaše údaje nikdy neopustia vaše zariadenie nešifrované a naše servery sú architektonicky znemožnené dešifrovať váš obsah.
Zistite viac o Redact PDF AI
Porovnanie funkcií
| Funkcia | anonym.legal | Redact PDF AI |
|---|---|---|
| Data Residency | Yes | Microsoft Azure (EU regions available) |
| Encryption Model | Yes | HTTPS in transit only |
| Provider Can Read Plaintext | Yes | Yes — plaintext uploads |
| Data Retention | Yes | 30 days |
| Schrems II Compliant | Yes | No |
| CLOUD Act Exposure | Yes | Yes (Microsoft / US jurisdiction) |
| Pricing | Free to €29/mo | $50–$250+/month |
| Entity Types | 285+ | Not documented |
| Language Support | 48 languages | Not documented |
| Reversible Encryption | AES-256-GCM | No |
| Detection Method | Yes | Proprietary AI (non-deterministic) |
| Audit Trail | Yes | Not found |
| Desktop App | Yes | No |
| ISO 27001 | Yes | Not found |
Porovnanie je založené na verejne dostupných informáciách. "Nenašlo sa" znamená, že funkcia nie je uvedená na stránke produktu. Posledná aktualizácia február 2026.
Prečo si vybrať anonym.legal
Hetzner Germany — No CLOUD Act Exposure
All processing runs on ISO 27001-certified servers in Germany. US law cannot compel access. Redact PDF AI uses Azure infrastructure subject to CLOUD Act jurisdiction.
Zero-Knowledge Architecture
Argon2id key derivation + AES-256-GCM encryption happens in your browser or desktop app. anonym.legal servers store only ciphertext they cannot decrypt. Redact PDF AI receives plaintext uploads.
Schrems II Compliant
Transfers to providers who can access plaintext violate GDPR Article 44 under Schrems II. Zero-knowledge encryption with user-held keys resolves this. Plaintext Azure uploads do not.
Zero Data Retention
anonym.legal retains no processed data. Redact PDF AI retains uploaded documents for 30 days on Azure servers.
285+ Entity Types, 48 Languages
Deterministic 3-layer NLP (Presidio + spaCy + XLM-RoBERTa) with per-entity confidence scoring and full audit trail. Not proprietary black-box AI.
Transparent Pricing
Free tier + €3–€29/month. Redact PDF AI charges $50–$250+/month with no free tier.
Kedy je anonym.legal správnou voľbou
anonym.legal je lepšie vhodné, keď:
- Spracovávate dokumenty podliehajúce GDPR, BDSG, NIS2 alebo HIPAA a potrebujete spracovanie kompatibilné so Schrems II
- Váš právny tím vyžaduje správcu údajov, ktorému je architektonicky znemožnené čítať váš obsah
- Potrebujete reverzibilné šifrovaní — dešifrujte anonymizované údaje pre audity alebo súdne príkazy
- Spracovávate dokumenty v 48 jazykoch, nie len po anglicky
- Rozpočet záleží — transparentné ceny až 10× nižšie ako Redact PDF AI
Často kladené otázky
Does Redact PDF AI comply with Schrems II and GDPR Article 44?
Redact PDF AI uploads documents to Microsoft Azure for processing, meaning Azure infrastructure has access to plaintext files. Under Schrems II (ECJ C-311/18), transfers to US providers who can access data in plaintext are incompatible with GDPR Article 44 without additional safeguards. anonym.legal’s zero-knowledge architecture — AES-256-GCM encryption before transmission, user-held keys, Hetzner Germany infrastructure — addresses this directly.
What is the CLOUD Act and why does it matter for PDF redaction?
The US CLOUD Act (2018) allows US law enforcement to compel US cloud providers to disclose data regardless of where it is stored. Data uploaded to Azure (Microsoft, a US company) is subject to CLOUD Act jurisdiction even if stored in EU regions. anonym.legal uses Hetzner, a German company on German infrastructure, and zero-knowledge encryption that prevents any party from accessing plaintext.
How long does Redact PDF AI retain uploaded documents?
Redact PDF AI retains uploaded documents for 30 days on Azure servers. anonym.legal has zero data retention — processed data is not stored on our servers. Users can delete their data at any time via the account dashboard.
Does anonym.legal support reversible redaction that Redact PDF AI lacks?
Yes. anonym.legal replaces PII with encrypted placeholders using AES-256-GCM. The original data can be restored by anyone with the decryption key — useful for legal audits, court-ordered disclosure, or internal review. Redact PDF AI permanently removes detected content with no recovery option.
How does detection accuracy compare?
anonym.legal uses a deterministic 3-layer NLP pipeline: Presidio (rule-based), spaCy/Stanza (statistical NLP), and XLM-RoBERTa (transformer models). Results are reproducible and auditable with per-entity confidence scores. Redact PDF AI uses proprietary AI that produces non-deterministic results — the same document may yield different redactions on successive runs, which is problematic for compliance documentation.
Anonymizácia PDF Zero-Knowledge
Kompatibilné s GDPR. Bezpečné zo Schrems II. Hetzner Nemecko. AES-256-GCM. Začnite zadarmo.
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.