Dashboard Structural Analysis anonym.plus SD1 LINKABILITY Case Study
← Previous Next →
anonym.plus SD1 LINKABILITY
Case Study 2 of 30

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.plus addresses this through 200+ entity types processed 100% locally via Presidio 2.2.357 sidecar — detection and anonymization that never leaves the device.

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.plus Addresses This

Detection Capabilities

anonym.plus identifies 200+ entity types including zip codes, dates of birth, gender markers, demographic quasi-identifiers. The local Presidio 2.2.357 + spaCy 3.8.11 architecture uses Presidio 2.2.357 deterministic recognizers with 121 built-in presets for structured identifiers and spaCy 3.8.11 with 23 language models, all running locally via FastAPI sidecar 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 local sidecar REST API (port 5002-5003) provides programmatic access to Presidio detection for local development workflow integration.

Compliance Mapping

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

anonym.plus’s GDPR (data never leaves device), HIPAA (local processing) compliance coverage, combined with 100% local — data never leaves device hosting, provides documented technical measures organizations can reference in their compliance documentation and regulatory submissions.

Product Specifications

SpecificationValue
App Versionv8.10.5
Entity Types200+ built-in, up to 50 custom
Detection EnginePresidio 2.2.357 + spaCy 3.8.11 (23 models)
Languages48 UI, 23 NLP models
Document FormatsPDF, DOCX, XLSX, TXT, CSV, JSON, XML + Image OCR
Anonymization MethodsReplace, Redact, Mask, Hash (SHA-256/512/MD5), Encrypt (AES-256-GCM)
ArchitectureTauri 2.x (Rust + React) + FastAPI sidecar (~370 MB)
PlatformsWin/Mac/Linux
LicensingEd25519 signed, machine-fingerprinted, max 5 machines
Processing100% local — data never leaves device
ComplianceGDPR, HIPAA (data residency guaranteed by local processing)
← Previous Next →