# NCSA AI Security Guidelines: lifecycle and governance

Locale: `en`

Source: `/en/compliance/ncsa-ai-security-guidelines/`

Summary: A summary of NCSA's AI Security Guidelines, covering the 7-phase secure AI lifecycle, governance, risk management, and practical testing focus areas.

On this page

1. [Overview](/en/compliance/ncsa-ai-security-guidelines/#topic-overview)
2. [Purpose and intended audiences](/en/compliance/ncsa-ai-security-guidelines/#purpose-and-audience)
3. [The secure AI lifecycle framework](/en/compliance/ncsa-ai-security-guidelines/#secure-ai-lifecycle)
4. [Governance, risk, and accountability](/en/compliance/ncsa-ai-security-guidelines/#governance-and-risk)
5. [Practical implementation focus](/en/compliance/ncsa-ai-security-guidelines/#implementation-focus)
6. [Requirements Matrix](/en/compliance/ncsa-ai-security-guidelines/#compliance-matrix)
7. [Readiness Assessment](/en/compliance/ncsa-ai-security-guidelines/#compliance-readiness-checklist)
8. [LLM-integrated App Pentest and AI Red Teaming](/en/compliance/ncsa-ai-security-guidelines/#ai-security-testing)
9. [Frequently Asked Questions](/en/compliance/ncsa-ai-security-guidelines/#compliance-faq)
10. [Related Frameworks](/en/compliance/ncsa-ai-security-guidelines/#related-compliance-frameworks)

# NCSA AI Security Guidelines: lifecycle and governance

A summary of NCSA's AI Security Guidelines, covering the 7-phase secure AI lifecycle, governance, risk management, and practical testing focus areas.

Executive Summary and Mandate Overview

Target Audience

Executives, AI development and operations teams, legal and DPO functions, and security teams using the NCSA guidance

Mandatory Frequency

Lifecycle-aligned (Phases 0 to 6, Concept through Disposal)

Required Scope

Prompts, models, APIs, training data, software supply chain, and surrounding software

Non-Compliance Risk

Prompt injection, jailbreaking, data poisoning, confidential-data leakage, and go-live without verification evidence

## Purpose and intended audiences

NCSA presents the document as guidance for developing, managing, and using AI systems securely and trustworthily.

[![Who uses the AI Security Guidelines: Executives, AI development and operations, Legal, privacy, and security, Auditors, Users and suppliers](/assets/compliance/guide-ncsa-ai-security-guidelines-purpose-and-audience-en-v1.webp)](/assets/compliance/guide-ncsa-ai-security-guidelines-purpose-and-audience-en-v1.webp)

**Who uses the AI Security Guidelines**

Each stakeholder has a distinct role linking risk, safeguards, and evidence across the AI lifecycle.

- **Executives** — Set direction, risk ownership, and accountability
- **AI development and operations** — Design, build, operate, and monitor the system
- **Legal, privacy, and security** — Govern requirements, data, and safeguards
- **Auditors** — Independently examine processes and evidence
- **Users and suppliers** — Use and support the system within defined boundaries

- It spans policy-level decision making for executives and technical practice for AI development and operations teams.
- Its intended stakeholders include legal and data-protection functions, cybersecurity teams, employees, customers, data subjects, and supply-chain vendors.
- The guidance draws on international standards and technical material including ISO/IEC, ENISA, and OWASP alongside Thai laws and practices.

## The secure AI lifecycle framework

The guidelines structure security controls across the full lifecycle, from pre-investment planning to decommissioning.

[![The seven-phase secure AI lifecycle: Concept → Secure Design → Secure Development → Secure Verification → Secure Deployment → Secure Operation and Maintenance → Disposal](/assets/compliance/guide-ncsa-ai-security-guidelines-secure-ai-lifecycle-en-v1.webp)](/assets/compliance/guide-ncsa-ai-security-guidelines-secure-ai-lifecycle-en-v1.webp)

**The seven-phase secure AI lifecycle**

Assign owners and evidence at each phase so security continues from concept to retirement.

1. **Concept** — Define needs and risks from the start
2. **Secure Design** — Identify threats and design safeguards
3. **Secure Development** — Protect data, code, and components
4. **Secure Verification** — Verify and test before deployment
5. **Secure Deployment** — Control release and configuration
6. **Secure Operation and Maintenance** — Monitor, maintain, and respond
7. **Disposal** — Retire the system and manage remaining data

- Phase 0: Concept - Identify business context, legal requirements, assets, threats, vulnerabilities, and risks before development.
- Phases 1-3: Secure Design, Secure Development, and Secure Verification.
- Phases 4-6: Secure Deployment, Secure Operations and Maintenance, and Proper Disposal.

## Governance, risk, and accountability

Governance uses the GRC framework and stresses that risk must be evaluated in each organization's specific context.

[![From risk ownership to AI governance: Assign roles, Integrate with ERM, Select safeguards, Audit and assurance, Communicate and train](/assets/compliance/guide-ncsa-ai-security-guidelines-governance-and-risk-en-v1.webp)](/assets/compliance/guide-ncsa-ai-security-guidelines-governance-and-risk-en-v1.webp)

**From risk ownership to AI governance**

AI risk needs accountable owners, decisions, evidence, and review.

- **Assign roles** — Define accountability and decision authority
- **Integrate with ERM** — Bring AI risks into enterprise risk management
- **Select safeguards** — Assign controls, owners, and evidence
- **Audit and assurance** — Examine conformity and effectiveness
- **Communicate and train** — Enable each role to perform its duties

- Document security-related roles, authority, and accountability for the AI system.
- Integrate AI risk into enterprise risk management and track relevant Thai laws and regulations.
- Establish auditing, certification, communication, and training for controllable, auditable operations.

## Practical implementation focus

The document recommends key measures to support auditing and retrospective review.

[![AI security measures that need evidence: Data provenance and quality, Component vulnerabilities, Prompt injection, AI red teaming, Logging and monitoring](/assets/compliance/guide-ncsa-ai-security-guidelines-implementation-focus-en-v1.webp)](/assets/compliance/guide-ncsa-ai-security-guidelines-implementation-focus-en-v1.webp)

**AI security measures that need evidence**

Selected safeguards need evidence that they work in the real AI system.

- **Data provenance and quality** — Verify data origin and suitability
- **Component vulnerabilities** — Examine software, libraries, APIs, and integrations
- **Prompt injection** — Test both direct and indirect paths
- **AI red teaming** — Simulate adversarial behavior within an authorized scope
- **Logging and monitoring** — Retain events, test results, and anomaly signals

- Establish Data Provenance and vulnerability scanning for processing software before launch.
- Test Direct and Indirect Prompt Injection, including jailbreaking, as described in the verification phase.
- Conduct AI Red Teaming and penetration testing across models, APIs, and surrounding software before go-live.

## Requirements and Testing Scope Matrix

Summary of the referenced clauses, the testing scope they cover, and the expected evaluation cycle.

| Reference | Mandate Title | Scope Required | Testing Cycle |
| --- | --- | --- | --- |
| **Phases 0 to 3 (NCSA AI)** | Concept, Secure Design, Secure Development, and Secure Verification | Threat models, training data, software supply chain, prompt injection, and AI red teaming | Before investment, development, and go-live decisions |
| **Phases 4 to 6 (NCSA AI)** | Secure Deployment, Operations and Maintenance, and Disposal | Secure baseline, prompt monitoring, APIs, and surrounding software | Pre-launch and throughout operations until disposal |

### Compliance Readiness Self-Assessment

Select items your organization has completed to evaluate your readiness score.

0%

Direct and Indirect Prompt Injection testing conducted on LLM-integrated applications
          
          
            
            AI red-teaming and jailbreaking evidence collected in the verification phase before go-live
          
          
            
            Training datasets audited for provenance and integrity to prevent Data Poisoning
          
          
            
            AI Red Teaming and penetration testing executed across models, APIs, and surrounding software prior to launch

Assessment Status

Check items above to view assessment result.

[Request Pentest Quote](/en/#contact)

STH AI SECURITY TESTING

## LLM-integrated App Pentest and AI Red Teaming

An LLM-integrated application has a wider attack surface than the model alone. The application, input paths, RAG or vector store, agent tools, identity, data, and event logging must be assessed together.

[![From AI scope to reproducible evidence: Map the system → Define scenarios → Test within controls → Collect evidence → Remediate and retest](/assets/compliance/guide-ncsa-ai-security-guidelines-ai-security-testing-en-v1.webp)](/assets/compliance/guide-ncsa-ai-security-guidelines-ai-security-testing-en-v1.webp)

**From AI scope to reproducible evidence**

Distinguish LLM-integrated application testing from AI red teaming and use evidence suited to each objective.

1. **Map the system** — Identify prompts, models, retrieval, tools, and trust boundaries
2. **Define scenarios** — Set risks, success criteria, and stop conditions
3. **Test within controls** — Use synthetic data and authorized scope
4. **Collect evidence** — Record reproducible results and impact
5. **Remediate and retest** — Assign owners and verify the outcome

### LLM-integrated application pentest

Validate controls at the system integration points, rather than limiting the assessment to model behaviour.

- User authorization, tenant and data separation, and data exposure through responses or retrieved documents.
- RAG, vector store, model-provider, API, and third-party tool integrations, including token and secret boundaries.
- Approval and authorization enforcement before an agent invokes a tool or performs an impactful action.

### AI Red Teaming

Simulate adversarial behaviour within an authorized scope to demonstrate whether guardrails and protective workflows work in practice.

- Prompt injection and indirect prompt injection through documents or data used as context.
- Jailbreaking or attempts to move the system outside its intended purpose, with validation of unsafe-output handling.
- Agentic-AI risks where a prompt or tool invocation could affect data, accounts, or downstream systems.

### Expected testing evidence

- An authorized scope, test environment and data, stop criteria, and emergency contacts.
- Evidence, severity, impact conditions, and remediation guidance that can be independently retested.
- A retest after remediation and a record of controls or risks that need production monitoring.

NCSA's Secure Verification phase gives active testing, LLM penetration testing for prompt injection and jailbreaking, data-leakage risks, and dangerous agent actions as examples of evidence to verify before release.

[Talk to STH about LLM-integrated App Pentest and AI Red Teaming](/en/#contact)

## Frequently Asked Questions (FAQ)

Key answers and practical guidance addressing common compliance questions.

### Which AI implementations fall within the scope of NCSA AI Security Guidelines?

The guidelines encompass traditional Machine Learning models as well as Generative AI and LLM systems deployed within enterprise environments or public services.

### How does security testing for LLM systems differ from standard web or API testing?

In addition to web and API vulnerabilities, the guidance calls for AI-specific verification such as prompt injection, jailbreaking, and AI red teaming across models, APIs, and surrounding software.

## Related Compliance Frameworks and Security Standards

- [
                NCSA Cloud Security Standard B.E. 2567 (2024)
                
              ](/en/compliance/ncsa-cloud-security-standard/)
- [
                NCSA Zero Trust Guidelines
                
              ](/en/compliance/ncsa-zero-trust-guidelines/)
- [
                Does ISO/IEC 27001:2022 require penetration testing?
                
              ](/en/compliance/iso-27001/)
- [
                Thailand Cybersecurity Act 2019 and penetration testing
                
              ](/en/compliance/cybersecurity-act/)

Open full-size image to zoom

## Official source documents

Original files from the regulating authorities, hosted on sth.sh for convenience. Always defer to the latest version at the source link.

[
            
              
              
              ![First-page preview of NCSA AI Security Guidelines](/assets/process/compliance-sources/sth-source-ncsa-ai-security-guidelines-2568.webp)
            
          ](/assets/documents/sth-source-ncsa-ai-security-guidelines-2568.pdf)

### NCSA AI Security Guidelines

By NCSA

[Open document (PDF) ](/assets/documents/sth-source-ncsa-ai-security-guidelines-2568.pdf)
              [Download ](/assets/documents/sth-source-ncsa-ai-security-guidelines-2568.pdf)
              
              [Source ](https://www.ncsa.or.th/standards)

## Need a pentest that satisfies these requirements?

Tell us about your systems and the requirements you must meet. The STH team will assess the approach and prepare a quotation.

[Request a Pentest quote](/en/#contact)

## PDF document

[Open in new tab ](/en/compliance/ncsa-ai-security-guidelines/)
              [Download](/en/compliance/ncsa-ai-security-guidelines/)

Last updated 16 October 2026