Limina
Overview
Product details compiled from public sources, each with a citation.
Matrix Coverage
Where this product defends, by asset class and NIST CSF function. The Coverage column shows whether each asset is Primary, Secondary, or Adjacent to what the product does. The table omits empty rows and columns.
| Asset class | Protect | Coverage | Source |
|---|---|---|---|
| Training Data | Primary | 4 | |
| Runtime AI Data | Secondary | 1 |
Framework Relevance
These frameworks include controls relevant to the asset classes Limina defends. This is an editorial inference from the AI Defense Matrix asset-level crossmap, not a statement that Limina implements these controls or is certified against them.
Expand Collapse
| Framework | Asset class | Relevant controls |
|---|---|---|
| NIST IR 8596 | Training Data | Training data |
| Runtime AI Data | Prompts (runtime); inference data | |
| CSA AI Controls Matrix | Training Data | Data Security and Privacy Lifecycle Management; Model Security |
| Runtime AI Data | Data Security and Privacy Lifecycle Management; Application and Interface Security | |
| ISO 42001 | Training Data | A.7 Data for AI systems |
| Runtime AI Data | A.7 Data for AI systems; A.8 Information for interested parties | |
| Google SAIF | Training Data | Secure training data; data-security foundations; dataset provenance and integrity |
| Runtime AI Data | Expand AI red-teaming; runtime input and output safety; prompt defense | |
| SANS Critical AI Security Guidelines | Training Data | Conventional Security Controls (defend training data; avoid data commingling); Data/Model Engineering Controls (data-quality controls; poison-robust training); Data Minimization and Obfuscation (differential privacy; synthetic data; federated learning) |
| Runtime AI Data | Model I/O Handling (sanitize, validate, and filter inputs and outputs; segregate user and system prompts; multilayered prompt-injection defense); Conventional Security Controls (protect augmentation and RAG data with vector-store access controls and validation); Data Minimization and Obfuscation (limit sensitive prompt content; context-window management); Limit Model Behavior (AI guardrails) | |
| MITRE ATLAS | Training Data | AML.T0020 Poison Training Data; AML.T0019 Publish Poisoned Datasets; AML.T0024.000 Infer Training Data Membership |
| Runtime AI Data | AML.T0051 LLM Prompt Injection; AML.T0054 LLM Jailbreak; AML.T0056 Extract LLM System Prompt | |
| OWASP AI Exchange | Training Data | Development-time threats: data poisoning, backdoor injection, dataset integrity violations |
| Runtime AI Data | Input threats: prompt injection, adversarial inputs, evasion; runtime threats: RAG poisoning, memory tampering | |
| OWASP LLM Top 10 | Training Data | LLM04 Data and Model Poisoning; LLM03 Supply Chain (dataset provenance) |
| Runtime AI Data | LLM01 Prompt Injection; LLM02 Sensitive Information Disclosure; LLM08 Vector and Embedding Weaknesses; LLM05 Improper Output Handling | |
| OWASP Agentic Security Top 10 | Training Data | ASI04 Agentic Supply Chain Vulnerabilities (dataset provenance and integrity) |
| Runtime AI Data | ASI06 Memory & Context Poisoning; ASI01 Agent Goal Hijack (via prompt injection in runtime inputs) |
Provenance
Last sourced 2026-06-25.
Expand Collapse
Sources
- Limina LLM workflow docs
- “This ensures confidential information remains safe while interacting with AI models”
- Limina about page
- Private AI rebrands to Limina
- Limina data de-identification page
- “Turn your most restricted data into fuel for AI, analytics, and research with data de-identification that works inside your own environment”
Changelog
-
Added to the catalog from the Limina documentation.
Found an error? Corrections are welcome. Suggest an edit.