Dashboard Structural Analysis anonym.legal SD1 LINKABILITY Case Study
← Previous Next →
anonym.legal SD1 LINKABILITY
Case Study 4 of 40

Anonymizing Machine Learning Models

Abigail Goldsteen, Gilad Ezov, Ron Shmelkin et al. (2020-07-26)

Research Source

Anonymizing Machine Learning Models
Abigail Goldsteen, Gilad Ezov, Ron Shmelkin et al. · 2020-07-26 · Source: arxiv

There is a known tension between the need to analyze personal data to drive business and privacy concerns. Many data protection regulations, including the EU General Data Protection Regulation (GDPR) and the California Consumer Protection Act (CCPA), set out strict restrictions and obligations on the collection and processing of personal data.

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 phone numbers, IMSI numbers, SIM identifiers, mobile network codes. 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

Replace is recommended for this pain point: substituting phone numbers with format-valid but non-functional alternatives maintains data structure while removing the PII anchor. Hash provides an alternative — deterministic hashing enables referential integrity across phone-linked records. 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 Article 9 special category data in sensitive contexts, ePrivacy Directive.

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 →