What you'll learn

Understand, at a basic level, what AI and Machine learning really is.
Understand the security challenges associated with AI
Identify opportunities to leverage AI in a secure way
Provide guidance to your organization for safe AI deployment

Course content

6 sections • 6 lectures • 1h 55m total length

AI Basics: What You Need to Know to Stay Secure22:43
After completing this lecture, you will be able to:
Explain what AI, machine learning, and deep learning actually are — and how they differ — without relying on jargon or hype
Describe how machine learning systems learn from data and why data quality directly drives the quality of AI decisions
Recognize where machine learning is already being used in everyday business tools like email filtering, fraud detection, hiring, and customer service
Distinguish between what ML systems can do (find patterns, make predictions) and what they cannot do (think, understand context, guarantee accuracy)
Identify how AI security differs from traditional IT security — specifically, why the risk lives in the data and decisions, not just the code
Evaluate an AI system or vendor by asking practical questions about data sourcing, model performance, and governance
Spot red flags that indicate an AI system lacks the transparency or oversight needed for responsible use
Apply healthy skepticism as a business skill when reviewing AI recommendations or assessing AI-driven tools
Evaluating an AI Vendor Pitch
AI Foundations Check

AI Risk Landscape: Real-World Threats You Need to Know23:19
AI misuse vs AI malfunction
Data poisoning (with notebook demo)
Adversarial inputs and model manipulation
Backdoored and Trojaned models
AI supply chain risks
Model inversion and membership inference (privacy attacks)
Model theft
Prompt injection and jailbreaks (with notebook demo)
Incident teardowns: Microsoft Tay, SolarWinds applied to AI, adversarial patches, poisoned review ecosystems
Monitoring and incident response fundamentals
AI Threat Recognition
Reporting an AI Incident to Your Manager

Hands-On AI Threat Modeling17:14
Give students a repeatable method for finding AI risks in their own systems
Identifying AI assets (models, data, prompts, infrastructure)
Mapping AI attack surfaces
STRIDE adapted for AI systems
OWASP Top 10 for LLMs as a threat modeling input
LLM-specific threat modeling
Red-teaming basics: scope, techniques, and reporting
Building a threat model for a sample AI application
Section 3
Red Team Scoping Meeting

Securing AI Systems in Production17:16
Why production is a different threat environment
Model hosting risks
API security for AI endpoints
Secrets management
Logging and monitoring AI behavior
Detecting jailbreak and abuse patterns
Rate limiting and abuse prevention
Secure deployment patterns
SOC-focused LLM incident runbook
Detection signals and alert patterns
Triage and severity mapping
Escalation, containment, and recovery workflows
Production Security Controls
Incident Triage Call

AI Governance, Compliance & Regulation19:28
Risk communication for executives
AI procurement: what to ask before you buy
Vendor evaluation frameworks
Policy creation and ownership
Incident response for AI systems at the leadership level
30/60/90-day minimum control baseline
30 days: immediate guardrails and policy minimums
60 days: monitoring, runbooks, and ownership model
90 days: governance cadence, audits, and improvement loop
Governance Quiz
Challenging a Shadow AI Discovery

Requirements

No programming experience needed. This course is for any professional seeking to understand the risks and rewards of AI

Description

AI is already making decisions in your organization — and most security teams aren't ready. This course closes that gap.

AI Security for Business Professionals is a practical, non-mathematical course for security analysts, managers, and developers who need to understand how AI systems can be attacked, defended, and governed — without a data science background.

You'll learn to identify real AI threats, build threat models for AI systems, harden AI deployments in production, and apply governance frameworks that satisfy auditors and executives alike.

What You'll Learn

How AI and machine learning actually work — intuition, not calculus
AI attack types: data poisoning, adversarial inputs, prompt injection, model theft, and backdoored models
OWASP Top 10 for LLMs — and how to apply it to real systems
AI threat modeling using STRIDE adapted for ML pipelines and LLM applications
How to secure AI APIs, manage secrets, and detect abuse patterns in production
AI governance, risk frameworks (NIST AI RMF, EU AI Act), and compliance essentials
How to communicate AI risk to executives, auditors, and non-technical stakeholders

Hands-On From Day One

Every module includes practical exercises. You'll run Jupyter notebooks that demonstrate data poisoning attacks, prompt injection exploits, and model behavior — then apply defenses. Role-play scenarios put you in real conversations with vendors, managers, and engineering leads so you can practice the skills that matter in the field.

Who This Course Is For

Security analysts and SOC professionals working with AI-powered tools
IT managers and security architects evaluating or deploying AI systems
Developers building or integrating LLM-based applications
Compliance and risk professionals responsible for AI governance
Business leaders who need to ask the right security questions about AI

No prior AI or machine learning experience required. If you can read a dashboard and write a risk memo, you're ready for this course.

Who this course is for:

Business professionals with concerned with Security and AI

What you'll learn

Explore related topics

Course content

AI Basics2 lectures • 23min

AI Security Landscape2 lectures • 23min

AI Threat Modeling2 lectures • 17min

Securing AI in Production2 lectures • 17min

AI Governance, Compliance & Regulation2 lectures • 19min

AI Security for Leadership1 lecture • 16min

Requirements

Description

Who this course is for: