AI+ Security Expert™
Protect and Secure: Leverage Intelligent AI Solutions
Certificate Code:
AT-2102
About This Course
This certification validates intermediate-level knowledge of AI-driven cybersecurity concepts and assesses competency in applying security controls, risk management practices, and AI-enabled threat detection techniques. The exam evaluates understanding of advanced security principles within AI-augmented environments.
Certificate Overview
Included
Instructor-led OR Self-paced course + Official exam + Digital badge
Duration
- Instructor-Led: 5 days (live or virtual)
- Self-Paced: 40 hours of content
Prerequisites
Interest in AI technologies, basic computer science knowledge, curiosity to learn, and awareness of AI ethics and data privacy.
Exam Format
50 questions, 70% passing, 90 minutes, online proctored exam
Course Modules
1
Module 1: AI Security Context, Scope and Opportunities
- 1.1 AI Security Scope and Enterprise Context
- 1.2 AI Security Roles and Responsibilities
- 1.3 AI Security Use Cases and Opportunities
- 1.4 Use Cases
- 1.5 Case Studies
2
Module 2: AI Application Architecture and Threat Modelling
- 2.1 AI Application Components
- 2.2 Assets, Trust Boundaries and Data Flows
- 2.3 Modern Cybersecurity Architecture
- 2.4 Threat Modelling for AI Applications
- 2.5 Use Cases
- 2.6 Case Studies
3
Module 3: Applied Python Automation for AI Security Evidence
- 3.1 Python for AI Security Tasks
- 3.2 Python Libraries for Security Engineering
- 3.3 Working with Security Data
- 3.4 Cybersecurity Data Analytics
- 3.5 Automation Patterns and Safe Scripting
- 3.6 Use Cases
- 3.7 Case Studies
4
Module 4: GenAI Application Security Controls
- 4.1 GenAI Application Components
- 4.2 Secure Design Patterns
- 4.3 Secure AI SDLC
- 4.4 Use Cases
- 4.5 Case Studies
5
Module 5: Prompt Injection, LLM Risk Testing, and Adversarial Attacks
- 5.1 Prompt Injection Techniques
- 5.2 Sensitive Information Disclosure Risks
- 5.3 Unsafe Output Handling
- 5.4 Use Cases
- 5.5 Case Studies
6
Module 6: RAG and Knowledge System Security
- 6.1 RAG System Architecture
- 6.2 RAG-Specific Risks
- 6.3 RAG Controls and Monitoring
- 6.4 Use Cases
- 6.5 Case Studies
7
Module 7: AI Data, Model, ML Pipeline and Detection Security
- 7.1 AI Data Security
- 7.2 Model and Artifact Security
- 7.3 ML Pipeline and MLSecOps Controls
- 7.4 AI-Based Detection and Model Monitoring
- 7.5 Adversarial ML Risks
- 7.6 Use Cases
- 7.7 Case Studies
8
Module 8: Secure AI Deployment: Cloud, API and Identity
- 8.1 AI Deployment Patterns
- 8.2 Identity and Secret Controls
- 8.3 Abuse Prevention and Cloud Controls
- 8.4 Use Cases
- 8.5 Case Studies
9
Module 9: AI Security Monitoring and Incident Response
- 9.1 AI Security Telemetry
- 9.2 Detection Engineering for AI Threats
- 9.3 AI Incident Response
- 9.4 Use Cases
- 9.5 Case Studies
10
Module 10: AI Governance, Privacy and Compliance
- 10.1 AI Governance Foundations
- 10.2 Privacy and Data Protection
- 10.3 Assurance Artifacts and Evidence
- 10.4 Use Cases
- 10.5 Case Studies
11
Module 11: Advanced Adversarial Testing, Red Teaming
- 11.1 Red Teaming Methodologies for AI Systems
- 11.2 Advanced Threat Vectors
- 11.3 Red Team Reporting
- 11.4 Use Cases
- 11.5 Case Studies
12
Module 12: Capstone Project
- 12.1 Proactive Threat Intelligence Dashboard
- 12.2 AI-Driven Cybersecurity Solution Development
- 12.3 AI-Powered SOC Automation
- 12.4 LLM Security Monitoring and Defense System
13
Optional Module: AI Agents Security Expert
- 1.1 What Are AI Agents?
- 1.2 Key Capabilities of AI Agents in Advanced Cybersecurity
- 1.3 Applications and Trends for AI Agents in Advanced Cybersecurity
- 1.4 How Does an AI Agent Work?
- 1.5 Core Characteristics of AI Agents
- 1.6 Types of AI Agents
AI Tools You'll Learn
CrowdStrike Falcon
Darktrace Enterprise
Vectra Cognito
SentinelOne Singularity
Cylance PROTECT
IBM QRadar Advisor with Watson
Exabeam Advanced Analytics
Rapid7 InsightIDR
Cynet 360
