Dashboard Structural Analysis anonym.legal SD1 LINKABILITY Case Study
← Previous Next →
anonym.legal SD1 LINKABILITY
Case Study 2 of 40

Autononym: Multimodal Anonymization of Health Data using Named Entity Recognition and Structured Medical Data Processing

Hamdi Yalin Yalic, Murat Dörterler, Alaettin Uçan et al. · Medical Technologies National Conference (2025-10-26)

Research Source

Autononym: Multimodal Anonymization of Health Data using Named Entity Recognition and Structured Medical Data Processing
Hamdi Yalin Yalic, Murat Dörterler, Alaettin Uçan et al. · Medical Technologies National Conference · 2025-10-26 · Source: semantic_scholar

This paper presents Autononym, an AI-powered software platform capable of robustly and scalably anonymizing health data across several formats, including unstructured free-text documents, tabular datasets, and medical images in both DICOM and standard RGB formats.

Executive Summary

This research paper examines a critical privacy challenge related to LINKABILITY — the ability to connect two pieces of information to the same person.

anonym.legal addresses this through 260+ entity types with 3-layer hybrid detection accessible via 6 platforms including Chrome Extension for real-time browser anonymization.

Root Cause: SD1 — LINKABILITY

The ability to connect two pieces of information to the same person. This is the foundational operation that makes PII dangerous. Nearly every pain point is an expression of linkability being created, exploited, or failing to be broken.

Irreducible truth: You cannot have useful data that is completely unlinkable AND completely useful. The very features that make data informative make it linkable. This is not a bug — it is information theory. The information content of a dataset and its linkability are the same property measured differently.

The Solution: How anonym.legal Addresses This

Detection Capabilities

anonym.legal identifies 260+ entity types including zip codes, dates of birth, gender markers, demographic quasi-identifiers. The 3-layer hybrid (Presidio + NLP + Stance classification) architecture uses Microsoft Presidio deterministic rules with checksum validations (Luhn, RFC-822) for structured identifiers and XLM-RoBERTa + Stanza NER with Stance classification for disambiguation for contextual references.

Anonymization Methods

Hash is recommended for this pain point: deterministic SHA-256 hashing enables referential integrity across datasets while preventing re-identification from original values. Replace provides an alternative — substituting quasi-identifiers with type labels removes re-identification potential while preserving data structure. For scenarios requiring reversibility, Encrypt (AES-256-GCM) enables authorized recovery of original values.

Architecture & Deployment

The REST API (Basic plan+, €3/month) provides programmatic PII detection with Bearer token auth. Rate limited to 100 req/min, max 100 KB per request — the most accessible API entry point in the ecosystem.

Compliance Mapping

This pain point intersects with GDPR Recital 26 identifiability test, Article 89 research safeguards.

anonym.legal’s GDPR, HIPAA, PCI-DSS, ISO 27001 compliance coverage, combined with Hetzner Germany, ISO 27001 certified hosting, provides documented technical measures organizations can reference in their compliance documentation and regulatory submissions.

Product Specifications

SpecificationValue
Platform Versionv7.4.4
Entity Types260+
Detection Layers3-layer: Presidio + NLP + Stance classification
Accuracy95.5% tested (42/44 tests)
Languages48
Anonymization MethodsReplace, Redact, Mask, Hash (SHA-256/512/MD5), Encrypt (AES-256-GCM)
PlatformsWeb App, Desktop, Office Add-in, MCP Server, Chrome Extension, REST API
PricingFree €0, Basic €3, Pro €15, Business €29
HostingHetzner Germany, ISO 27001
ComplianceGDPR, HIPAA, PCI-DSS, ISO 27001
← Previous Next →