Securing AI E-Learning Training

The Securing AI Training helps you develop the skills needed to secure AI and Large Language Model applications. This training covers the key security risks related to LLMs, prompt-based attacks, adversarial techniques, data protection, model security, infrastructure security, secure deployment and API security.

Demo Securing AI E-Learning Training

The training prepares learners to build and manage secure, trustworthy AI systems across the full development lifecycle. You will explore LLM security fundamentals, threat modeling and risks aligned with the OWASP Top 10 for LLM Applications. You will also learn practical mitigation strategies for prompt injection and other prompt-based attacks.

In addition to technical security controls, the training addresses AI governance, ethics, compliance and risk management. This helps you understand how security connects with responsible AI practices and the development of trustworthy AI systems.

What will you learn?

• Understand the fundamentals of LLM security
• Apply threat modeling to AI and LLM applications
• Recognize OWASP-aligned risks for LLM applications
• Identify prompt-based attacks and adversarial techniques
• Apply mitigation strategies against prompt injection and other AI attacks
• Protect data, models, infrastructure and AI supply chains
• Apply secure deployment practices for AI systems
• Use API security principles for AI and LLM applications
• Design defense-in-depth architectures for secure AI systems
• Understand AI governance, ethics, compliance and risk management
• Recognize emerging threats and future trends in AI security
• Apply the covered concepts through a capstone project guide

Who should attend?

This training is suitable for:

• AI Developers
• Security Engineers
• Cybersecurity Professionals
• DevSecOps Engineers
• Software Developers working with AI or LLMs
• IT Architects
• Cloud Security Professionals
• Risk and Compliance Professionals
• AI Governance Professionals
• Technology Leaders who want to build secure AI systems

Course Outcome

This training includes one main track: Security.

Track 1: Security

In this track, learners begin with the foundations of LLM security and threat modeling. You will learn how to assess security risks in LLM applications and how these risks align with the OWASP Top 10 for LLM Applications.

You will then examine prompt-based attacks, adversarial techniques and effective mitigation strategies. The track continues with the security of data, models, infrastructure and AI supply chains. You will also explore best practices for secure deployment, API protection and defense-in-depth architectures that protect AI systems across the development lifecycle.

The track also covers AI governance, ethics, compliance and risk management. Finally, you will explore advanced threats, emerging trends and practical application through a capstone project guide.

This LearningKit with more than 6 hours of learning is divided into three tracks:

Securing AI: LLM Threat Modeling & OWASP Alignment

Course: 49 Minutes

• Course Overview
• The LLM Threat Landscape and Adversarial Risks
• OWASP LLM Top 10 Risk Categories
• Threat Modeling Frameworks
• Knowledge Check: Understanding LLM Threats and Risk Modeling
• Traditional Threats Within an LLM Context
• The CIA Triad and Generative AI
• Conducting LLM Threat Modeling
• Knowledge Check: Applying Traditional Threat Principles to LLMs
• Course Summary

Securing AI: Introduction to LLM Security

Course: 43 Minutes

• Course Overview
• Generative AI and LLM Fundamentals
• Historical AI Security Incidents
• Enterprise Relevance of LLM Security
• Knowledge Check: Exploring LLM Security Foundations and Enterprise Risk
• LLM Terminology and Key Concept
• Agentic AI and Tool Calling Risks
• Exploring LLM Behavior and Risk Awareness
• Knowledge Check: Examining LLM Behavior and Agentic AI Risk Essentials
• Course Summar

Securing AI: Prompt-Based Attacks and Mitigations

Course: 43 Minutes

• Course Overview
• Direct Prompt Injection
• Indirect Prompt Injection
• Defensive Prompt Engineering
• Knowledge Check: Securing LLMs: Prompt Injection and Defense Strategies
• Input Pre-Filtering and Sanitization
• Real-World Attack Case Studies
• Simulating and Defending Against Prompt Attacks
• Knowledge Check: Defending LLMs: Input Pre-Filtering and Attack Analysis
• Course Summary

Securing AI: Data, Model, & Infrastructure Security

Course: 48 Minutes

• Course Overview
• Data Poisoning Risks
• Model Theft and IP Protection
• Sensitive Information Leakage
• Supply Chain and Third-Party Risks
• Knowledge Check: Securing the AI Stack: Data, Models, and Third Parties
• Threat Mitigation Frameworks
• Dataset Lineage, Consent, and Data Residency
• Model Registry and Artifact Integrity
• Detecting Poisoned Data and Using a Model Registry
• Knowledge Check: Managing AI Risk: Lineage, Registries, and Detection
• Course Summary

Securing AI: Secure Deployment & API Security

Course: 47 Minutes

• Course Overview
• Secure Deployment Practices
• API Security for LLMs
• Downstream System Safety
• Knowledge Check: Reviewing Security Practices for AI Deployments and LLMs
• RAG and Multi-Tool Security
• Secure AI SDLC and CI/CD
• Configuring Secure Deployments
• Knowledge Check: Building Secure RAG Pipelines: Logging and CI/CD
• Course Summary

Securing AI: AI Governance, Ethics, & Compliance

Course: 54 Minutes

• Course Overview
• Responsible AI Principles
• Regulatory Compliance Affecting AI Systems
• AI Governance Frameworks
• AI Bias Detection and Mitigation
• Knowledge Check: Reviewing Responsible AI Policy, Governance, and Fairness
• Transparency and Reporting in AI Systems
• AI Ownership, Oversight, and Shutdown Authority
• Mapping Internal AI Policy to External Standards
• Performing a Governance Framework Review
• Knowledge Check: Assessing AI Governance Ownership, Reporting, and Mapping
• Course Summary

Securing AI: Defense-in-Depth Strategies & Security Tools

Course: 55 Minutes

• Course Overview
• Defense-in-Depth Architecture
• Monitoring and Anomaly Detection
• Red Teaming LLMs
• AI Security Tool Evaluation
• Knowledge Check: Reviewing Layered AI Security: Monitor, Test, and Evaluate
• Continuous Improvement Practices
• AI Incident Response and Abuse Handling
• Balancing Security and Velocity
• Implementing Monitoring and Incident Response
• Knowledge Check: Assessing AI Security Response, Monitoring, and Balance
• Course Summary

Securing AI: Advanced Threats, Future Trends, & Capstone Project Guide

Course: 29 Minutes

• Course Overview
• Emerging Threats and LLM Trends
• Advanced Defensive Techniques for AI Security
• Knowledge Check: Applying Advanced Defenses to LLM Threats
• Capstone Project Guidance
• AI Security: Case Study Analysis
• Knowledge Check: Building a Secure RAG Assistant: Capstone Guide
• Course Summary

Assessment:

• Final Exam: Agentic AI - Foundations, Architectures, and Frameworks