AI Security Fundamentals
A foundation in how AI systems are attacked, how they are protected, and how AI is used against organizations, for every professional who works with AI.
About this program
AI is now part of everyday work, from writing assistants and coding tools to customer-facing chatbots and automated decision systems. Each introduces risks that most professionals were never trained to recognize.
This program gives a structured foundation across all seven domains of the IIAS Body of Knowledge. It explains how AI systems work and fail, the main classes of attack against them, the controls that apply across the AI lifecycle, and the ways adversaries use AI against people and processes.
Concepts are reinforced through guided lab exercises in a safe environment. The program is the recommended starting point for anyone new to AI security and the common foundation for every IIAS learning path.
Who it is for
Intended for
- Professionals who use, procure or oversee AI tools
- Security, IT and risk staff new to AI-specific threats
- Managers and team leads responsible for AI adoption
- Public servants and regulators working on AI policy
Recommended background
- General professional experience in any field
- Basic familiarity with workplace technology
- No prior AI, programming or security knowledge required
What you will be able to do
- Explain how machine learning models, LLMs and AI agents work and where they fail
- Describe the main classes of attack on AI systems using recognized taxonomies
- Identify security controls that apply at each stage of the AI lifecycle
- Recognize prompt injection and unsafe use of AI assistants
- Recognize indicators of deepfakes, voice-clone fraud and AI-scaled phishing
- Describe the purpose of NIST AI RMF, ISO/IEC 42001 and the EU AI Act
Curriculum
Six modules, completed in order. Each module ends with a short knowledge check; four include a graded lab exercise.
The AI security landscapeWhy AI changes cybersecurity
- How AI changes both attack and defense
- The three pillars: security for AI, with AI and from AI
- Key terms and the structure of the Body of Knowledge
How AI systems work and failModels, data, LLMs and agents
- The machine learning lifecycle, from data to deployment
- How large language models and AI agents operate
- Mapping the attack surface of an AI-enabled system
Attacks on AI systemsDomains 1 and 3
- Evasion, poisoning, model extraction and inference attacks
- Direct and indirect prompt injection
- Using MITRE ATLAS and the OWASP Top 10 for LLM Applications
Controls across the AI lifecycleDomains 2 and 4
- Data, training and model supply-chain controls
- Secure deployment, access control and monitoring
- Safe use of AI tools in daily work
- How security teams use AI, and why oversight matters
AI-enabled threats to people and processesDomain 7
- Deepfake audio, video and images
- Voice-clone fraud and AI-scaled phishing
- Verification steps that defeat impersonation
Governance and accountabilityDomains 5 and 6
- Roles and accountability for AI use
- Overview of NIST AI RMF, ISO/IEC 42001 and the EU AI Act
- Risk classification and acceptable use
- The role of testing and assurance
Graded lab exercises
Each exercise has defined objectives that are checked on completion. All exercises run in an isolated training environment.
Map the attack surface of an AI assistant
Identify the data sources, tools, users and integrations of a sample assistant, and where each could be abused.
Harden an AI assistant for daily work
Review an assistant's settings, judge everyday uses against safe-use rules, and recognize and respond to signs that it was influenced by content it read.
Spot synthetic media and verify a high-risk request
Assess audio and video samples for synthetic indicators and apply a verification procedure to a payment request.
Classify AI use cases by risk
Assign risk levels and required controls to a set of AI use cases for a fictional organization.
Body of Knowledge coverage
How deeply this program covers each domain of the IIAS Body of Knowledge.
| Domain | Coverage |
|---|---|
| 1AI threat landscape and adversarial ML | Applied |
| 2Secure AI lifecycle | Introduced |
| 3LLM and agentic AI security | Applied |
| 4AI-augmented security operations | Introduced |
| 5AI governance, risk and compliance | Applied |
| 6AI assurance and evaluation | Introduced |
| 7Synthetic media and identity defense | Applied |
Core: assessed in depth. Applied: practiced in exercises. Introduced: concepts and terminology.
On completion
Completing all modules, knowledge checks and graded labs gives you:
Program certificate
The IIAS Certificate in AI Security Fundamentals, with a unique ID for verification, listing the Body of Knowledge domains covered.
8 CE hours
8 continuing education (CE) hours recorded on completion, which other certifying bodies may accept under their own rules.
Membership eligibility
Eligibility to take the membership assessment, the second step of the membership pathway.
Continue with a program for your role
Explore more IIAS training
Browse all programs, or see how completing a program leads to IIAS membership.
Get IIAS updates
AI Threat Lab advisories, briefing invitations, new training programs and Body of Knowledge editions, in one email list.
