anonym.plus
Licensed desktop — v8.10.5
30Case Studies
3Drivers
3Solid
0Structural Limits
200+Entity Types
SD1
LINKABILITY
SOLIDThe core technical problem the ecosystem solves. The anonymize.solutions platform provides a dual-layer detection engine: Layer 1 — 210+ regex recognizers (246 patterns, 75+ country formats, checksum-validated) for deterministic PII; Layer 2 — spaCy (25 langs) + Stanza (7 langs) + XLM-RoBERTa (16 langs) for probabilistic NER. Then 5 anonymization methods break the link: Replace, Redact, Mask, Hash, Encrypt (AES-256-GCM). 260+ entity types across 48 languages — each one a linkability-breaking operation.
- 01TÉCNICAS PARA ANONIMIZAR DADOS SENSÍVEIS EM SISTEMAS DE INFORMAÇÃO
- 02Autononym: Multimodal Anonymization of Health Data using Named Entity Recognition and Structured Medical Data Processing
- 03OpenAIRE webinar - Amnesia: High-accuracy Data Anonymization
- 04Anonymizing Machine Learning Models
- 05Towards formalizing the GDPR's notion of singling out.
- 06From t-closeness to differential privacy and vice versa in data anonymization
- 07A Survey on Current Trends and Recent Advances in Text Anonymization
- 08Reconsidering Anonymization-Related Concepts and the Term “Identification” Against the Backdrop of the European Legal Framework
- 09The lawfulness of re-identification under data protection law
- 10Blinded Anonymization: a method for evaluating cancer prevention programs under restrictive data protection regulations
SD2
IRREVERSIBILITY
SOLIDIf PII is never collected server-side, there is nothing to propagate. cloak.business runs 100% air-gapped with local NLP models — PII never touches a network. anonym.plus processes via local Presidio sidecar with Ed25519 machine-bound licensing. The architecture makes irreversibility structurally impossible — you cannot leak what you never collected.
- 01GDPR and Large Language Models: Technical and Legal Obstacles
- 02Balancing AI Innovation and Privacy: A Study of Facial Recognition Technologies under the DPDPA
- 03A Formal Model for Integrating Consent Management Into MLOps
- 04GDPR Safeguards for Facial Recognition Technology: A Critical Analysis
- 05Comparative Analysis of Passkeys (FIDO2 Authentication) on Android and iOS for GDPR Compliance in Biometric Data Protection
- 06De-Identification of Facial Features in Magnetic Resonance Images: Software Development Using Deep Learning Technology
- 07Privacy in Italian Clinical Reports: A NLP-Based Anonymization Approach
- 08Clinical de-identification using sub-document analysis and ELECTRA
- 09DICOM De-Identification via Hybrid AI and Rule-Based Framework for Scalable, Uncertainty-Aware Redaction
- 10GDPR Fine: Mercadona S.A. — Spanish Data Protection Authority (aepd) (Spain)
SD5
COMPLEXITY CASCADE
SOLIDanonymize.solutions offers 3 tiers that each eliminate different layers from the attack surface: Self-Managed (Docker, air-gapped) removes cloud dependency. Managed Private (EU infrastructure, customer key mgmt) removes shared-tenancy risk. Online SaaS minimizes deployment complexity. Plus 6 integration points each operating at a different layer.
- 01Systematic review of privacy-preserving Federated Learning in decentralized healthcare systems
- 02[Anonymization of general practitioners' electronic medical records in two research datasets].
- 03A Comprehensive Evaluation of Privacy-Preserving Mechanisms in Cloud-Based Big Data Analytics: Challenges and Future Research Directions
- 04Privacy Risk Assessment Frameworks for Large-Scale Medical Datasets Using Computational Metrics
- 05Data Obfuscation Through Latent Space Projection for Privacy-Preserving AI Governance: Case Studies in Medical Diagnosis and Finance Fraud Detection
- 06Turkish data protection law: GDPR alignment and key 2024 amendment
- 07AI Meets Anonymity: How named entity recognition is redefining data privacy
- 08Viewing the GDPR through a de-identification lens: a tool for compliance, clarification, and consistency
- 09Mitigating AI risks: A comparative analysis of Data Protection Impact Assessments under GDPR and KVKK
- 10Approaches for Anonymization Methods in IoT Preservation Privacy
| Product Specifications | |
|---|---|
| App Version | v8.10.5 |
| Entity Types | 200+ built-in, up to 50 custom |
| Detection Engine | Presidio 2.2.357 + spaCy 3.8.11 (23 models) |
| Languages | 48 UI, 23 NLP models |
| Document Formats | PDF, DOCX, XLSX, TXT, CSV, JSON, XML + Image OCR |
| Anonymization Methods | Replace, Redact, Mask, Hash (SHA-256/512/MD5), Encrypt (AES-256-GCM) |
| Architecture | Tauri 2.x (Rust + React) + FastAPI sidecar (~370 MB) |
| Platforms | Win/Mac/Linux |
| Licensing | Ed25519 signed, machine-fingerprinted, max 5 machines |
| Processing | 100% local — data never leaves device |
| Compliance | GDPR, HIPAA (data residency guaranteed by local processing) |
Other Product Case Studies
Research Basis
Case studies on this page are grounded in peer-reviewed research. A sample of foundational papers:
- Fracacio & Dallilo (2025). Técnicas para Anonimizar Dados Sensíveis em Sistemas de Informação.
- Yalic et al. (2025). Autononym: Multimodal Anonymization of Health Data using Named Entity Recognition.
- Terrovitis (2023). OpenAIRE Amnesia: High-accuracy Data Anonymization.
Full citation metadata available in each case study page JSON-LD.