Security & Compliance

Enterprise-Grade Security

Automated PII/NHI/secret detection, ACL-aware retrieval, immutable audit logs, and zero-trust AI — all on-premise.

Back to Home
Defence in Depth

Security at
every layer

CordonData is designed with the assumption that no single security control is sufficient. Each layer independently prevents a class of threat — so a failure in one layer doesn't compromise the whole system.

Identity verified before any request is processed

SSO via Keycloak — no local passwords, no shared credentials

Access decisions made on live ACL state, not cached tokens

Source-of-truth permissions synced continuously from your systems

Sensitive content detected and flagged before it reaches the AI

PII, NHI, and secret patterns scanned automatically on ingest

Every action logged with who, what, when, and outcome

Immutable audit trail — required for GDPR, HIPAA, and internal reviews

Layer 1 — Identity & Authentication
Keycloak SSO · MFA support · JWT token validation
GATE 1
Layer 2 — Authorisation & ACL
Role-based capabilities · Live permission sync · Per-document access
GATE 2
Layer 3 — Compliance Scanning
PII · NHI · Secrets · Configurable scan rules · Redaction
GATE 3
Layer 4 — Immutable Audit Log
Every query · Every access · Every admin action · CSV export
GATE 4
Request approved — compliant content delivered to authorised user
Detection Coverage

What CordonData scans for

Three independent scanning layers detect sensitive content before it enters the AI pipeline — and flag it for remediation.

PII
Personal Identifiable Information
22 types
Person name Email address Phone number Postal address Date of birth Passport number Driver licence National ID Tax ID Bank account Credit card IBAN SSN / NHS Medical condition IP address Biometric ID + 6 more
NHI
Non-Human Identities & Workload Creds
13 types
AWS IAM Role ARN AWS STS assumed role Azure managed identity Azure service principal GCP service account GCP workload identity GitHub Actions OIDC OIDC workload subject SPIFFE ID K8s service account + 3 more
Secrets
Credential Material & API Keys
35+ types
AWS access keys Azure storage key Google API key GitHub PAT GitLab PAT Docker PAT Slack token JWT tokens SSH private key Stripe keys Twilio API key DB connection strings Private key blocks High-entropy secrets + 21 more
Burn (destructive redact)

Permanently remove sensitive content from the document and purge it from the AI index. Irreversible. Audit logged.

Mark Safe

Acknowledge a finding as intentional or acceptable. Removes the compliance block so the document re-enters the AI pipeline.

Re-scan

Trigger a fresh scan with the latest detection rules. Automatically runs when the scanner taxonomy is updated.

Enterprise-Ready, by Design

Built from the ground up for the security, compliance, and scale requirements of the world's most demanding organizations.

Air-Gapped Ready

Zero external API calls

AES-256 Encryption

At rest & in transit

Docker / Kubernetes

Single-node to multi-AZ

Keycloak SSO

AD, LDAP, OIDC, SAML

On-Premise

Deploy entirely within your data center. Air-gapped operation with no external dependencies. Full control over infrastructure, networking, and data residency.

  • Bare metal or VM deployment
  • Docker Compose or Kubernetes
  • Local LLM inference via Ollama

BYOC (Bring Your Own Cloud)

Deploy inside your own AWS, Azure, or GCP environment. You maintain control of the infrastructure while we provide the software and support.

  • Your VPC, your security groups
  • Your IAM roles and policies
  • Your encryption keys (BYOK)

Managed Single-Tenant

Let us host it for you — in a dedicated, physically isolated environment. No shared databases, no shared indexes, no cross-tenant data leakage.

  • Dedicated infrastructure per customer
  • 99.9% uptime SLA
  • Managed updates & monitoring
// COMPLIANCE_ENGINE

Automated PII, NHI & Secret Detection

Before any document enters your AI pipeline, CordonData scans, classifies, and redacts sensitive data — ensuring compliance with GDPR, HIPAA, PCI-DSS, and internal data governance policies.

PII Detection

Automatically identify and classify Personally Identifiable Information across all ingested documents — names, addresses, phone numbers, email addresses, social security numbers, passport numbers, driver's license IDs, and more.

SSN Email Phone Passport DL# DOB

NHI Detection

Detect Non-public Health Information and protected health data — medical record numbers, health insurance IDs, patient identifiers, diagnosis codes, and clinical trial data — ensuring HIPAA compliance.

MRN HIPAA ICD-10 HITECH

Secret & Credential Detection

Scan for leaked API keys, access tokens, database connection strings, private keys, AWS/Azure/GCP credentials, and other secrets accidentally embedded in documents before they reach the AI model.

API Key Token ConnStr PEM

How Compliance Scanning Works

1
Ingest

Document enters the pipeline from any connected source

2
Scan & Classify

Regex + ML models detect PII, NHI, and secrets with confidence scoring

3
Redact or Flag

Auto-redact sensitive spans or flag for manual review based on policy

4
Index Safely

Only sanitized content enters the vector index and LLM context window

Enterprise-Grade Transparency

We built CordonData to solve the two biggest blockers for Enterprise AI adoption: Data Security and Hallucinations.

// RETRIEVAL_AUDIT_TRACE

Verifiable Retrieval Audit Trace

LLM hallucinations are unacceptable in the enterprise. CordonData provides a deterministic audit trace for every generated sentence. Instantly verify the exact document, page number, and extracted text chunk the AI used to formulate its response.

  • Direct links to source files in your DMS
  • Confidence scoring on vector matches
  • Exact text chunk highlighting
AI Response
Generated in 1.2s
Based on the current guidelines, the Q3 bonus pool has been increased by 15% across the APAC division [1].
Audit Trace: Reference [1]
MATCH_SCORE: 0.94
DOC: APAC_Project_Phoenix_Launch_Brief.pdf
PAGE: 12 | CHUNK: #402
"...the executive board has approved a 15% increase to the bonus pool specifically allocated for the APAC division following record sales..."
JS
John Smith Role: HR Director
Query: "Q3 Layoffs"
Found 4 matching documents.
Indexing Source: Enterprise_DMS/HR_Confidential
ED
Emma Doe Role: Engineering Intern
Query: "Q3 Layoffs"
No results found.
Filtered by Index Authorization Rules
// ZERO_TRUST_ACL

Permission-Safe Retrieval Routing

A search engine is only as safe as its weakest access control. While Keycloak handles seamless identity authentication, CordonData’s native authorization engine takes over at the data layer. When a user queries the system, the vector space is dynamically filtered by cross-referencing their username, group, and authority directly against the indexed document metadata.

  • Secure authentication via Keycloak/Active Directory
  • Index-level authorization (User/Group matching)
  • Impossible to bypass via prompt injection

Ready to transform how your team works with documents?

Join enterprise teams using CordonData for secure, AI-powered document management — deployed on your infrastructure.