AI Security Fundamentals Course

Lesson 1 · Video

AI Security Fundamentals Intro

Lesson 2 · Video

Module 1: AI Risk Management & Program Governance

Lesson 3 · Video

The AI Risk Landscape

The AI risk landscape encompasses the broad range of threats, vulnerabilities, and uncertainties associated with artificial intelligence systems. In this lesson, learners will explore the major categories of AI risk, including data, model, operational, and ethical risks, while examining how these differ from traditional cybersecurity and IT risks. The lesson also highlights the business, regulatory, and reputational consequences of poorly managed AI systems through real-world examples. Understanding the AI risk landscape is essential for security professionals, business leaders, and governance teams seeking to implement responsible, trustworthy, and resilient AI systems.

Lesson 3 · Video

Building an AI Security Program

This lesson explores how organizations build structured AI security programs that align security objectives with business goals, governance requirements, and risk management practices. Learners will examine the key components of an effective AI security program, including governance structures, policies, accountability frameworks, performance metrics, and continuous improvement processes. The lesson explains how organizations operationalize AI security through clear ownership, measurable objectives, and mature governance practices that support trustworthy and resilient AI systems.

Lesson 5 · Video

AI Risk Registers & Control Catalogs

This lesson introduces AI risk registers and control catalogs as foundational tools for managing AI-related risks within an organization. Learners will explore how AI risks are identified, categorized, scored, prioritized, and mapped to security and governance controls. The lesson explains how organizations use structured risk management practices to improve accountability, support compliance, and maintain visibility into evolving AI threats. Students will gain practical knowledge of how risk registers support governance decisions and how control catalogs align AI risks with established security frameworks and standards.

Lesson 6 · Video

Integrating AI Risk into Enterprise GRC

This lesson explores how AI risks are integrated into Enterprise Governance, Risk, and Compliance (GRC) programs. Learners will examine how organizations extend existing risk management frameworks to include AI-specific risks, establish ownership and accountability, align AI governance with audit and compliance functions, and maintain traceability from risk identification through mitigation. The lesson demonstrates how enterprise GRC programs provide the structure necessary to manage AI risks consistently, support regulatory readiness, and strengthen organizational trust in AI systems.

Lesson 7 · Video

Metrics & Executive Reporting

This lesson examines how organizations measure AI security performance and communicate AI-related risks to executive leadership. Learners will explore the differences between Key Performance Indicators (KPIs) and Key Risk Indicators (KRIs), identify common sources of AI security metrics, and understand how dashboards, heat maps, and executive reports support governance and decision-making. The lesson emphasizes the importance of translating technical findings into business-relevant insights that enable leaders to make informed decisions regarding AI risk, security, compliance, and organizational trust.

Lesson 8 · Video

Module 2: Data Security, Privacy & Model Confidentiality

Lesson 9 · Video

Data Classification for AI Pipelines

This lesson introduces data classification as a foundational component of AI data governance and security. Learners will explore how organizations categorize AI data according to sensitivity and business value, apply classification labels throughout the AI lifecycle, and align security controls with data classifications. The lesson also examines metadata tagging, label propagation, retention requirements, and governance practices that help protect sensitive information while supporting compliance, accountability, and trustworthy AI operations.

Lesson 10 · Video

Secure Data Lifecycle

This lesson examines how organizations secure data throughout its entire lifecycle within AI environments. Learners will explore how data is collected, stored, processed, transmitted, retained, and ultimately deleted while maintaining confidentiality, integrity, and availability. The lesson covers encryption, access controls, secure processing techniques, retention policies, audit logging, and lifecycle governance practices that help organizations protect sensitive information and support compliance requirements across modern AI systems.

Lesson 11 · Video

Privacy Engineering & Differential Privacy

This lesson explores privacy engineering as a foundational discipline for protecting individuals within AI systems. Learners will examine privacy-by-design principles, differential privacy, k-anonymity, l-diversity, and synthetic data techniques used to reduce privacy risks while maintaining analytical value. The lesson also addresses the balance between data utility and privacy protection, demonstrating how organizations integrate privacy safeguards into AI development and operations to support trust, compliance, and responsible innovation.

Lesson 12 · Video

Federated & Distributed Learning Security

This lesson explores the security challenges and protections associated with federated and distributed learning environments. Learners will examine how AI models can be trained across multiple devices or organizations without centralizing sensitive data, while understanding the risks introduced by decentralized architectures. The lesson covers federated learning attack surfaces, secure aggregation, homomorphic encryption, device trust, confidentiality controls, governance considerations, and security-by-design practices that help organizations build secure and trustworthy distributed AI ecosystems.

Lesson 13 · Video

Regulatory Compliance in Data Use

This lesson examines the regulatory and compliance requirements that govern the collection, processing, storage, sharing, and use of data within AI systems. Learners will explore major privacy and data protection regulations, including GDPR, CCPA, PIPEDA, and emerging AI governance frameworks. The lesson explains how organizations establish compliant data practices, manage consent, support data subject rights, maintain accountability, and align AI operations with evolving legal and regulatory expectations across multiple jurisdictions.

Lesson 14 · Video

Module 3: Secure Model, Development, Architecture & MLOps

Lesson 15 · Video

Threat Modeling AI Systems

This lesson introduces threat modeling as a foundational practice for securing AI systems. Learners will explore how organizations identify potential threats, adversaries, attack surfaces, vulnerabilities, and security controls throughout the AI lifecycle. The lesson examines how traditional threat modeling approaches are adapted for AI environments, including risks associated with data pipelines, machine learning models, inference services, and AI infrastructure. By understanding how attackers target AI systems, learners will be better prepared to design resilient architectures, prioritize security investments, and reduce organizational risk.

Lesson 16 · Video

Secure Feature Engineering

This lesson explores secure feature engineering and its role in protecting AI systems from security, privacy, and integrity risks. Learners will examine how raw data is transformed into model-ready features, identify threats that emerge during feature creation, and understand how governance controls help ensure trustworthy inputs. The lesson covers feature stores, data leakage, feature poisoning, privacy considerations, validation processes, and security controls that help organizations maintain the reliability and integrity of machine learning systems.

Lesson 17 · Video

Model Hardening & Robustness

This lesson explores model hardening and robustness testing as critical components of AI security. Learners will examine how organizations strengthen machine learning models against adversarial attacks, manipulation attempts, unexpected inputs, and operational failures. The lesson covers adversarial machine learning, robustness evaluation, stress testing, red teaming, validation frameworks, and resilience engineering practices that help organizations improve the security, reliability, and trustworthiness of AI systems operating in real-world environments.

Lesson 18 · Video

Secure Dev Environments & Sandboxing

This lesson explores secure development environments and sandboxing practices used to protect AI systems throughout development, testing, and deployment. Learners will examine how organizations secure AI engineering workflows, isolate workloads, manage dependencies, and reduce the risk of compromise within development pipelines. The lesson covers development environment security, container isolation, sandboxing technologies, access controls, secrets management, and secure engineering practices that support resilient and trustworthy AI systems.

Lesson 19 · Video

Reproducibility & Provenance

This lesson explores model reproducibility and provenance as essential capabilities for trustworthy AI systems. Learners will examine how organizations track datasets, features, models, configurations, and training processes to ensure consistent results and maintain accountability throughout the AI lifecycle. The lesson covers provenance records, lineage tracking, version control, experiment management, auditability, and governance practices that help organizations demonstrate trust, compliance, and operational reliability.

Lesson 20 · Video

Secure AI System Architecture

This lesson explores secure AI system architecture and the principles used to design resilient, trustworthy, and secure AI platforms. Learners will examine architectural components across the AI lifecycle, including data pipelines, model services, inference systems, APIs, monitoring platforms, and governance controls. The lesson explains how security-by-design, defense-in-depth, segmentation, trust boundaries, and operational resilience help organizations build AI systems capable of resisting threats while supporting business objectives and regulatory requirements.

Lesson 21 · Video

Module 4: AI Supply Chain, Adversarial Defense & Incident

Lesson 23 · Video

Secure CI/CD for Models

This lesson explores secure CI/CD practices for machine learning models and AI systems. Learners will examine how organizations automate model development, testing, validation, approval, and deployment while maintaining strong security controls. The lesson covers MLOps pipelines, artifact verification, policy enforcement, automated testing, model promotion workflows, deployment governance, and supply chain protections that help ensure AI models reach production environments safely and securely.

Lesson 24 · Video

Model Registry & Feature Store Security

This lesson explores the security and governance controls required to protect model registries and feature stores within modern AI environments. Learners will examine how these repositories support machine learning operations, why they represent high-value targets, and how organizations secure them through access controls, encryption, lineage tracking, monitoring, and governance processes. The lesson emphasizes the importance of protecting AI assets throughout their lifecycle while maintaining trust, traceability, and operational integrity.

Lesson 25 · Video

Secrets & Credential Management

This lesson explores secrets and credential management within AI environments. Learners will examine how organizations protect API keys, access tokens, passwords, certificates, encryption keys, and service credentials that support AI systems. The lesson covers secret lifecycle management, secure storage, credential rotation, privileged access controls, vault technologies, workload identity, and governance practices that reduce the risk of credential compromise while supporting secure AI operations.

Lesson 26 · Video

Runtime Isolation & Policy Enforcement

This lesson explores runtime isolation and policy enforcement mechanisms used to secure AI systems after deployment. Learners will examine how organizations control workload behavior, restrict access, enforce governance requirements, and reduce operational risk during real-world AI operations. The lesson covers runtime isolation technologies, policy engines, zero trust principles, workload identity, authorization controls, guardrails, and continuous enforcement strategies that help organizations maintain secure and trustworthy AI environments.

Lesson 27 · Video

Adversarial Attacks & Defenses

This lesson explores adversarial attacks and defensive strategies designed to protect AI systems from manipulation, deception, and abuse. Learners will examine how attackers exploit weaknesses in machine learning models through techniques such as adversarial examples, evasion attacks, poisoning, model extraction, and prompt injection. The lesson also covers defensive controls, resilience engineering, adversarial training, monitoring, validation, and governance practices that help organizations strengthen the security and trustworthiness of AI systems.

Lesson 28 · Video

AI Red Teaming & Evaluation Framework

Lesson 29 · Video

Module 5: Governance, Assurance & Responsible AI

Lesson 30 · Video

Global Regulatory Overview

This lesson provides an introduction to the global regulatory landscape shaping artificial intelligence governance, security, and compliance. Learners will explore major frameworks including the European Union AI Act, the NIST AI Risk Management Framework, and ISO/IEC 42001. The lesson examines how governments and standards bodies are responding to the rapid growth of AI technologies through risk-based regulation, accountability requirements, and governance expectations. Understanding these frameworks helps organizations build trustworthy AI systems, reduce compliance risk, and align security practices with evolving international standards.

Lesson 31 · Video

ISO/IEC 42001 & 23894 Implementation

This lesson explores the implementation of ISO/IEC 42001 and ISO/IEC 23894, two internationally recognized standards that help organizations establish structured AI governance and risk management programs. Learners will examine how AI management systems support accountability, oversight, continuous improvement, and regulatory readiness. The lesson covers governance structures, risk assessments, documented controls, operational processes, audits, and organizational responsibilities that help ensure AI systems are developed and managed in a trustworthy, secure, and responsible manner.

Lesson 32 · Video

AI System of Record & Vendor Risk

This lesson explores AI Systems of Record and Vendor Risk Management, two essential components of effective AI governance programs. Learners will examine how organizations maintain visibility into AI assets, document system ownership, track model inventories, and govern third-party AI providers. The lesson covers AI inventories, system registries, vendor due diligence, risk assessments, contractual controls, monitoring activities, and governance practices that help organizations maintain accountability, transparency, and trust across increasingly complex AI ecosystems.

Lesson 33 · Video

Audit Evidence & Assurance Reporting

This lesson explores audit evidence and assurance reporting within AI governance programs. Learners will examine how organizations collect, maintain, validate, and present evidence demonstrating that AI systems operate in accordance with governance, security, compliance, and risk management requirements. The lesson covers evidence collection, audit readiness, control testing, assurance activities, documentation practices, and reporting processes that help organizations demonstrate accountability, transparency, and trustworthiness across the AI lifecycle.

Lesson 34 · Video

Model Assurance Reporting

This lesson explores Model Assurance Reporting and the processes organizations use to evaluate, document, and communicate the trustworthiness of AI models. Learners will examine how performance, security, fairness, reliability, robustness, and compliance considerations are assessed and reported throughout the model lifecycle. The lesson covers assurance frameworks, model documentation, reporting structures, stakeholder communication, and governance practices that help organizations demonstrate accountability and confidence in deployed AI systems.

Lesson 35 · Video

Responsible AI Frameworks & Ethics

This lesson explores Responsible AI Frameworks and Ethics and examines how organizations translate ethical principles into practical governance, risk management, and operational controls. Learners will explore fairness, accountability, transparency, privacy, human oversight, and societal impact considerations that influence trustworthy AI development. The lesson covers leading responsible AI frameworks, ethical decision-making processes, governance structures, and implementation practices that help organizations build AI systems aligned with organizational values, stakeholder expectations, and regulatory requirements.

Lesson 36 · Video

Algorithmic Impact Assessment (AIA)

This lesson explores Algorithmic Impact Assessments (AIAs) and how organizations evaluate potential risks, harms, and societal impacts before deploying AI systems. Learners will examine structured assessment methodologies used to identify privacy concerns, fairness issues, security risks, operational impacts, and governance obligations. The lesson covers risk categorization, stakeholder analysis, mitigation planning, documentation requirements, and decision-making processes that help organizations deploy AI systems responsibly and in alignment with regulatory and governance expectations.

Lesson 37 · Video

Executive & Board Reporting

This lesson explores Executive and Board Reporting within AI governance programs. Learners will examine how organizations communicate AI risks, governance activities, assurance findings, compliance obligations, and strategic considerations to senior leadership and governing bodies. The lesson covers reporting frameworks, governance metrics, risk communication, decision-making support, accountability structures, and board oversight responsibilities that help organizations ensure AI systems remain aligned with business objectives, regulatory expectations, and risk management priorities.

Lesson 38 · Assessment

AI Security Final Exam