AI Defense Matrix Catalog

Citadel AI

Visit official site ↗

Overview

Product details compiled from public sources, each with a citation.

Vendor
Citadel AI2
Description
Maker of Citadel Lens, which tests AI models and datasets against industry standards and generates AI compliance reports for regulations such as the EU AI Act.4
Deployment
Self-hosted4
Status
Active1
Compliance
ISO 270015 (company-level, see Methodology)

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 Detect Coverage
AI Model Primary 4
Training Data Secondary 4
Runtime AI Data Secondary 3

Framework Relevance

These frameworks include controls relevant to the asset classes Citadel AI defends. This is an editorial inference from the AI Defense Matrix asset-level crossmap, not a statement that Citadel AI implements these controls or is certified against them.

Expand Collapse
Framework Asset class Relevant controls
NIST IR 8596 AI Model Models; Algorithms (model configuration)
Training Data Training data
Runtime AI Data Prompts (runtime); inference data
CSA AI Controls Matrix AI Model Model Security; Governance, Risk and Compliance
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 AI Model A.6 AI system life cycle; A.10 Third-party and customer relationships; A.5 Assessing impacts of AI systems
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 AI Model Protect the AI model; ensure model integrity, provenance, and weight security
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 AI Model Conventional Security Controls (protect model parameters with least privilege, encryption at rest, runtime obfuscation, and trusted execution environments); Data/Model Engineering Controls (adversarial training; alignment and fine-tuning); AI Supply Chain Management (public-model caution; transfer-attack exposure)
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 AI Model AML.T0043 Craft Adversarial Data; AML.T0024 Exfiltration via AI Inference API (subtechniques: AML.T0024.001 Invert AI Model and AML.T0024.002 Extract AI Model); AML.T0018 Manipulate AI Model (integrity and backdoor)
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 AI Model Development-time and runtime model threats: model inversion, extraction, evasion, poisoning
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 AI Model LLM03 Supply Chain; LLM04 Data and Model Poisoning; LLM09 Misinformation
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 AI Model ASI04 Agentic Supply Chain Vulnerabilities (model provenance, weights, and dynamic loading)
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 2026-06-10.

Expand Collapse

Sources

  1. Citadel AI homepage
    Vendor source accessed 2026-06-10
  2. Citadel AI about page
    Vendor source accessed 2026-06-10
  3. Lens for LLMs launch announcement
    Vendor source accessed 2026-07-04
    • “allowing you to automatically evaluate factual consistency, answer relevancy, toxicity, jailbreak detection, and more”
  4. Citadel Lens product page
    Vendor source accessed 2026-06-10
    • “Citadel Lens provides powerful explainability features to understand AI models.”
    • “After testing, Lens automatically creates reports: model quality reports, data quality reports, ISO technical reports, process reports, and more.”
  5. Citadel AI Trust Center
    Vendor source accessed 2026-06-13
    • “Our information security systems are ISO 27001:2022 certified, and we work with Vanta to ensure the continuous compliance of our security measures.”

Changelog

  1. Added verbatim source quotes to coverage and compliance citations.

  2. Updated compliance attestation source quote.

  3. Added to the catalog from the Citadel AI website.

Found an error? Corrections are welcome. Suggest an edit.