Comparison
Same documents. Measured results.
Compare detection on a shared corpus, then consider where your documents are processed. Two different questions when choosing a tool.
| Detector | Strict recall | Leaks prevented | False positives |
|---|---|---|---|
| Anoni (models + rules) | 94.8 % | 99.0 % | 73 |
| openai/privacy-filter (raw) | 67.8 % | 91.9 % | 217 |
| Microsoft Presidio (fr) | 58.6 % | 77.1 % | 356 |
| AInonymizer | 64.4 % | 67.9 % | 143 |
| Anoni (rules only) | 59.3 % | 65.2 % | 0 |
Strict recall: data found in the correct category, with ≥ 66% overlap. Leaks prevented: share of sensitive characters covered, across all categories. These results describe this corpus and these configurations; they do not guarantee the outcome on your document. Read the methodology →
The real difference: where it runs
Numbers aside, the line that matters is simple. Anoni runs on your machine: no document, no excerpt leaves it, and it works offline after the first launch. An online anonymizer sends the text to a server to process it.
For a law firm or an accounting practice, that decides the question before it is asked: with local processing there is no recipient, no hosting, no transfer to document. With a cloud service, the text leaves the machine. So you check where it is processed, by whom, and under which contract.
About the systems compared
Microsoft Presidio is an open-source library from Microsoft for detecting and redacting personal data. It is general-purpose, multilingual, configurable. The numbers above use its French configuration, as shipped.
Anoni is built for French documents. It pairs detection models with rules that validate structured identifiers (NIR, SIRET, IBAN) against their checksums rather than guessing them from a pattern. The detection models are open (CamemBERT under MIT, the ONNX runtime under Apache-2.0); the application itself is not open source.
And on data we didn’t write
A synthetic bench is still our bench. So Anoni is also measured on an independent corpus, ai4privacy OpenPII: real French personal data, hand-annotated, under an open license (CC-BY). 500 documents we didn’t write.
On Anoni’s French scope (people, addresses, places, emails, phone numbers, dates): 92.7 % strict recall and 97.1 % of sensitive characters covered. An independent measurement, on real data.
Questions
On 210 synthetic French legal documents, Anoni reaches 94.8% strict recall against 58.6% for Microsoft Presidio (French configuration), same documents and same scoring rule. Presidio is a general-purpose library; Anoni is tuned for French documents and validates structured identifiers (NIR, SIRET, IBAN) with their checksums.