Private AI

Detects personally identifiable information, protected health information, payment card data, and confidential company information across 50+ entity types by analyzing semantic context rather than pattern matching alone. Unlike regex-based approaches, the system reads contextual relationships between tokens to distinguish legitimate uses of PII-like strings (e.g., 'John' as a common noun vs. a person's name) and handles real-world data quality issues including ASR errors, OCR mistakes, handwritten forms, and conversational disfluencies. Supports 52 languages including code-switching scenarios.

Redacts, pseudonymizes, or synthetically replaces detected PII entities across text, documents, images, and audio using configurable transformation strategies. The system applies entity-specific redaction rules (e.g., masking credit card numbers with asterisks, replacing names with consistent pseudonyms, generating synthetic replacements) while preserving document structure and downstream usability. Supports batch processing across multiple file formats (PDF, DOCX, XLS, XLSX, PPTX, XML, JSON, CSV) and image formats (TIFF, PNG, JPEG with OCR-based redaction).

Detects PII across 52 languages including support for code-switching (mixing multiple languages within the same document or conversation). The system handles language-specific entity formats (e.g., different date formats, phone number patterns, address structures across countries) and recognizes PII in multilingual contexts without requiring explicit language specification. Supports real-world multilingual data including conversational transcripts with language mixing.

Detects and redacts PII in images and scanned documents by performing optical character recognition (OCR) to extract text and then applying context-aware PII detection to the extracted content. The system handles real-world image quality issues including poor resolution, skewed text, handwritten annotations, and partial visibility. Supports TIFF, PNG, and JPEG formats and can redact detected PII directly in the image output.

Detects PII in audio files and speech transcripts by handling automatic speech recognition (ASR) errors, conversational disfluencies, and real-world speech patterns. The system recognizes that ASR output contains errors and uses contextual analysis to identify PII despite transcription mistakes (e.g., 'John' transcribed as 'Jon', 'Smith' as 'Smyth'). Supports audio file input and transcript text with conversational patterns including filler words, interruptions, and informal speech.

De-identifies structured data formats (JSON, XML, CSV) by applying schema-aware redaction that preserves data structure and enables downstream processing. The system understands structured data schemas and applies entity-specific redaction rules to relevant fields while maintaining referential integrity and data relationships. Supports nested structures, arrays, and complex data hierarchies.

Connects related PII entities across multiple documents and extracts relationships between detected entities to maintain data consistency and enable entity resolution. The system identifies when the same person, organization, or account appears across different documents (e.g., matching 'John Smith' in one document with 'J. Smith' in another) and tracks relationships (e.g., 'patient John Smith was treated by Dr. Jane Doe'). This enables consistent pseudonymization where the same entity receives the same replacement across a dataset.

Deploys the de-identification engine as a containerized service within customer infrastructure (on-premises or customer VPC) ensuring sensitive data never leaves the customer's network. The system runs as a Docker container in the customer's environment, processes data locally, and returns only de-identified results. This architecture enables compliance with strict data residency requirements (HIPAA, GDPR, CCPA) and eliminates data transmission risk to third-party servers.

Provides cloud-hosted de-identification API where data is processed in Limina's managed infrastructure across multiple geographic regions (US, Canada, UK, Germany, Japan, Hong Kong, Australia, Switzerland). The SaaS model offers managed scaling, automatic updates, and no infrastructure management burden, with data processed in region-specific endpoints to support data residency compliance. Customers can choose between on-premises and SaaS deployment based on compliance and operational requirements.

Integrates de-identification capabilities directly into data warehouse and cloud marketplace environments (Snowflake, AWS Marketplace, Azure Marketplace) enabling PII detection and redaction within existing data pipelines without external API calls. The integration allows customers to apply de-identification transformations as SQL functions or native data processing steps within their warehouse, reducing data movement and enabling privacy-preserving analytics on sensitive data in place.

Enables customers to fine-tune the de-identification model for domain-specific PII patterns and custom entity types not covered by the standard 50+ entity types. The system allows training on customer data to recognize industry-specific sensitive information (e.g., internal employee IDs, proprietary account numbers, domain-specific medical codes) and improve accuracy on customer-specific data distributions. Fine-tuning is performed in collaboration with Limina's technical team as part of onboarding.

Provides expert determination reports and compliance documentation from independent partners validating de-identification effectiveness and regulatory compliance. The system generates reports demonstrating that de-identification meets standards for HIPAA Safe Harbor, GDPR anonymization, CCPA compliance, and other regulatory frameworks. Reports are prepared by independent experts and can be used for regulatory audits, compliance demonstrations, and legal defensibility.

Provides a Python SDK for integrating de-identification capabilities directly into Python applications, data pipelines, and ML workflows. The SDK abstracts API complexity and enables developers to call de-identification functions with simple Python method calls, handle responses programmatically, and integrate de-identification into data processing pipelines without managing HTTP requests or authentication directly.

Exposes de-identification capabilities through a high-throughput REST API supporting real-time and batch processing of PII detection and redaction requests. The API processes billions of requests per month in production (per product claims) and supports concurrent requests with documented rate limiting and quota management. API endpoints handle text, documents, images, and audio with configurable response formats and transformation strategies.