SecureWorld Boston 2026

Upon completion of this course, attendees will have an up-to-date understanding of how AI works, AI implementation options, AI threats and vulnerabilities, AI security controls standards, best practices for building an AI security program, and assessing risks assessing AI security risks. The course covers technical security controls applied to AI systems and underlying infrastructure before, during, and after a cyberattack. Finally, administrative security capabilities, including AI governance, risk management, compliance, and audit considerations will be discussed.

Today’s companies develop, deploy, access AI applications and workloads through many computing environments including public cloud, private cloud, multi-cloud, hybrid cloud, and on-premises. These AI implementations and operations involve the risk of one or more cyberattacks that target the AI systems directly (model tampering, agent manipulation, data poisoning, GPU runtime exploits, etc.) or target the underlying infrastructure (public cloud, private cloud, on-premises, etc.) where the AI systems reside. The various development and deployment solutions make securing high-risk AI systems a challenge. A comprehensive AI cybersecurity program should account the various of development / deployment / operations scenarios.

The objective of this class is to help organizations design, develop, build, and manage high-risk AI systems and the underlying cloud, multi-cloud, hybrid cloud, on-premises environments that support AI systems throughout design, development, deployment, and operations. The course deliverables are grouped into six modules which cover key topics related to building a highly effective AI Security Program.

Module 1: What is Artificial Intelligence (AI) and how does AI work?

Includes an overview of Artificial Intelligence (AI) including how AI works (applications and workloads), AI architecture, components, and processes (models, algorithms, workflows). Module 1 includes topics such as AI Models (Generative AI, Large Language Models (LLMs), foundation models), and Multi-Agent Systems (MAS). A review of AI Use Cases across multiple industry sectors is included.

Module 2: AI Cloud Adoption Frameworks (CAFs)

An AI Cloud Adoption Framework (CAF) provides a structured approach to adopting AI solutions effectively and responsibly. It is designed to guide organizations through the process of implementing AI workloads ensuring scalability, security, and operational excellence. Topics include developing, deploying, and securing AI solutions in Microsoft Azure Cloud, Amazon Web Services (AWS), Google Cloud Platform (GCP) and Oracle Cloud Infrastructure (OCI). Deployment models include IaaS (bring your AI), PaaS (build your AI), and SaaS (buy your AI).

Module 3: AI threats and Vulnerabilities

AI Threats include those related to AI models, the data such models are trained and tested on, the third-party components, plug-ins, and libraries utilized in their development, as well as the platform models are hosted on.  Topics include an overview of the FS-ISAC Adversarial AI Framework, MITRE ATLAS (a framework that provides adversary profiles, techniques, and mitigations for securing AI-enabled systems), and OWASP Agentic AI Threats. Module 3 also includes a discussion of AI vulnerabilities including data related vulnerabilities and model related vulnerabilities. Topics include the OWASP Top 10 for LLM Applications (2025) and the OWASP Top 10 for Agentic Applications (2026).

Module 4: AI security controls

Includes an overview of NIST SP 800-218A Secure Software Development Framework (SSDF) for AI, the Google Secure AI Framework (SAIF), the OWASP AI Security and Privacy Guide, and the Cloud Security Alliance AI Controls Matrix (AICM). NIST SP 800-218A provides secure software development practices specifically for generative AI and dual-use foundation models. The Google Secure AI Framework (SAIF) provides guidance for securing AI systems, including the SAIF Risk Self-Assessment to help build and deploy AI systems securely. The OWASP AI Security and Privacy Guide provides clear and actionable insights on designing, creating, testing, and procuring secure and privacy-preserving AI systems. The AI Controls Matrix (AICM) is a comprehensive framework developed by the Cloud Security Alliance (CSA) to help organizations align their AI practices with international standards and regulations. 

Module 5: Building an AI Security Program

This module focuses on building a comprehensive AI security program to protect AI systems (in development and in production) as well as a security program for the underlying multi-cloud / hybrid-cloud solution. NIST SP 800-18 Rev. 2 Developing Security, Privacy, and Cybersecurity Supply Chain Risk Management Plans for Systems outlines the essential components of a System Security Pan (SSP), which documents security requirements for a system and describes the controls in place or planned to meet those requirements.  NIST SP 1800-35 Implementing a Zero Trust Architecture, which includes a discussion on enabling secure authorized access to enterprise resources distributed across on-premises and multiple cloud environments.  Module 5 also includes is a summary of NIST practices for Assessing Risks and Impacts of AI (ARIA) which supports three evaluation levels: model testing, red-teaming, and field testing.

Module 6: AI governance, AI risk management, AI compliance, AI audit  

This module Includes an overview of AI Governance, Compliance and AI Audit requirements. AI governance includes processes, standards and guardrails that help ensure AI systems and tools are safe and ethical. Includes an overview of NIST-AI-600-1, Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile and companion document AI RMF Playbook. The profile helps organizations identify unique risks posed by generative AI and proposes actions for generative AI risk management that best aligns with their goals and priorities. AI compliance refers to the decisions and practices that enable businesses to stay in line with the laws and regulations that govern the use of AI systems. AI audit requirements focus on ensuring transparency, accountability, and compliance in AI systems.

Upon completion of this course, attendees will have an up-to-date understanding of how AI works, AI implementation options, AI threats and vulnerabilities, AI security controls standards, best practices for building an AI security program, and assessing risks assessing AI security risks. The course covers technical security controls applied to AI systems and underlying infrastructure before, during, and after a cyberattack. Finally, administrative security capabilities, including AI governance, risk management, compliance, and audit considerations will be discussed.

Today’s companies develop, deploy, access AI applications and workloads through many computing environments including public cloud, private cloud, multi-cloud, hybrid cloud, and on-premises. These AI implementations and operations involve the risk of one or more cyberattacks that target the AI systems directly (model tampering, agent manipulation, data poisoning, GPU runtime exploits, etc.) or target the underlying infrastructure (public cloud, private cloud, on-premises, etc.) where the AI systems reside. The various development and deployment solutions make securing high-risk AI systems a challenge. A comprehensive AI cybersecurity program should account the various of development / deployment / operations scenarios.

The objective of this class is to help organizations design, develop, build, and manage high-risk AI systems and the underlying cloud, multi-cloud, hybrid cloud, on-premises environments that support AI systems throughout design, development, deployment, and operations. The course deliverables are grouped into six modules which cover key topics related to building a highly effective AI Security Program.

Module 1: What is Artificial Intelligence (AI) and how does AI work?

Includes an overview of Artificial Intelligence (AI) including how AI works (applications and workloads), AI architecture, components, and processes (models, algorithms, workflows). Module 1 includes topics such as AI Models (Generative AI, Large Language Models (LLMs), foundation models), and Multi-Agent Systems (MAS). A review of AI Use Cases across multiple industry sectors is included.

Module 2: AI Cloud Adoption Frameworks (CAFs)

An AI Cloud Adoption Framework (CAF) provides a structured approach to adopting AI solutions effectively and responsibly. It is designed to guide organizations through the process of implementing AI workloads ensuring scalability, security, and operational excellence. Topics include developing, deploying, and securing AI solutions in Microsoft Azure Cloud, Amazon Web Services (AWS), Google Cloud Platform (GCP) and Oracle Cloud Infrastructure (OCI). Deployment models include IaaS (bring your AI), PaaS (build your AI), and SaaS (buy your AI).

Module 3: AI threats and Vulnerabilities

AI Threats include those related to AI models, the data such models are trained and tested on, the third-party components, plug-ins, and libraries utilized in their development, as well as the platform models are hosted on.  Topics include an overview of the FS-ISAC Adversarial AI Framework, MITRE ATLAS (a framework that provides adversary profiles, techniques, and mitigations for securing AI-enabled systems), and OWASP Agentic AI Threats. Module 3 also includes a discussion of AI vulnerabilities including data related vulnerabilities and model related vulnerabilities. Topics include the OWASP Top 10 for LLM Applications (2025) and the OWASP Top 10 for Agentic Applications (2026).

Module 4: AI security controls

Includes an overview of NIST SP 800-218A Secure Software Development Framework (SSDF) for AI, the Google Secure AI Framework (SAIF), the OWASP AI Security and Privacy Guide, and the Cloud Security Alliance AI Controls Matrix (AICM). NIST SP 800-218A provides secure software development practices specifically for generative AI and dual-use foundation models. The Google Secure AI Framework (SAIF) provides guidance for securing AI systems, including the SAIF Risk Self-Assessment to help build and deploy AI systems securely. The OWASP AI Security and Privacy Guide provides clear and actionable insights on designing, creating, testing, and procuring secure and privacy-preserving AI systems. The AI Controls Matrix (AICM) is a comprehensive framework developed by the Cloud Security Alliance (CSA) to help organizations align their AI practices with international standards and regulations. 

Module 5: Building an AI Security Program

This module focuses on building a comprehensive AI security program to protect AI systems (in development and in production) as well as a security program for the underlying multi-cloud / hybrid-cloud solution. NIST SP 800-18 Rev. 2 Developing Security, Privacy, and Cybersecurity Supply Chain Risk Management Plans for Systems outlines the essential components of a System Security Pan (SSP), which documents security requirements for a system and describes the controls in place or planned to meet those requirements.  NIST SP 1800-35 Implementing a Zero Trust Architecture, which includes a discussion on enabling secure authorized access to enterprise resources distributed across on-premises and multiple cloud environments.  Module 5 also includes is a summary of NIST practices for Assessing Risks and Impacts of AI (ARIA) which supports three evaluation levels: model testing, red-teaming, and field testing.

Module 6: AI governance, AI risk management, AI compliance, AI audit  

This module Includes an overview of AI Governance, Compliance and AI Audit requirements. AI governance includes processes, standards and guardrails that help ensure AI systems and tools are safe and ethical. Includes an overview of NIST-AI-600-1, Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile and companion document AI RMF Playbook. The profile helps organizations identify unique risks posed by generative AI and proposes actions for generative AI risk management that best aligns with their goals and priorities. AI compliance refers to the decisions and practices that enable businesses to stay in line with the laws and regulations that govern the use of AI systems. AI audit requirements focus on ensuring transparency, accountability, and compliance in AI systems.

Upon completion of this course, attendees will have an up-to-date understanding of how AI works, AI implementation options, AI threats and vulnerabilities, AI security controls standards, best practices for building an AI security program, and assessing risks assessing AI security risks. The course covers technical security controls applied to AI systems and underlying infrastructure before, during, and after a cyberattack. Finally, administrative security capabilities, including AI governance, risk management, compliance, and audit considerations will be discussed.

Today’s companies develop, deploy, access AI applications and workloads through many computing environments including public cloud, private cloud, multi-cloud, hybrid cloud, and on-premises. These AI implementations and operations involve the risk of one or more cyberattacks that target the AI systems directly (model tampering, agent manipulation, data poisoning, GPU runtime exploits, etc.) or target the underlying infrastructure (public cloud, private cloud, on-premises, etc.) where the AI systems reside. The various development and deployment solutions make securing high-risk AI systems a challenge. A comprehensive AI cybersecurity program should account the various of development / deployment / operations scenarios.

The objective of this class is to help organizations design, develop, build, and manage high-risk AI systems and the underlying cloud, multi-cloud, hybrid cloud, on-premises environments that support AI systems throughout design, development, deployment, and operations. The course deliverables are grouped into six modules which cover key topics related to building a highly effective AI Security Program.

Module 1: What is Artificial Intelligence (AI) and how does AI work?

Includes an overview of Artificial Intelligence (AI) including how AI works (applications and workloads), AI architecture, components, and processes (models, algorithms, workflows). Module 1 includes topics such as AI Models (Generative AI, Large Language Models (LLMs), foundation models), and Multi-Agent Systems (MAS). A review of AI Use Cases across multiple industry sectors is included.

Module 2: AI Cloud Adoption Frameworks (CAFs)

An AI Cloud Adoption Framework (CAF) provides a structured approach to adopting AI solutions effectively and responsibly. It is designed to guide organizations through the process of implementing AI workloads ensuring scalability, security, and operational excellence. Topics include developing, deploying, and securing AI solutions in Microsoft Azure Cloud, Amazon Web Services (AWS), Google Cloud Platform (GCP) and Oracle Cloud Infrastructure (OCI). Deployment models include IaaS (bring your AI), PaaS (build your AI), and SaaS (buy your AI).

Module 3: AI threats and Vulnerabilities

AI Threats include those related to AI models, the data such models are trained and tested on, the third-party components, plug-ins, and libraries utilized in their development, as well as the platform models are hosted on.  Topics include an overview of the FS-ISAC Adversarial AI Framework, MITRE ATLAS (a framework that provides adversary profiles, techniques, and mitigations for securing AI-enabled systems), and OWASP Agentic AI Threats. Module 3 also includes a discussion of AI vulnerabilities including data related vulnerabilities and model related vulnerabilities. Topics include the OWASP Top 10 for LLM Applications (2025) and the OWASP Top 10 for Agentic Applications (2026).

Module 4: AI security controls

Includes an overview of NIST SP 800-218A Secure Software Development Framework (SSDF) for AI, the Google Secure AI Framework (SAIF), the OWASP AI Security and Privacy Guide, and the Cloud Security Alliance AI Controls Matrix (AICM). NIST SP 800-218A provides secure software development practices specifically for generative AI and dual-use foundation models. The Google Secure AI Framework (SAIF) provides guidance for securing AI systems, including the SAIF Risk Self-Assessment to help build and deploy AI systems securely. The OWASP AI Security and Privacy Guide provides clear and actionable insights on designing, creating, testing, and procuring secure and privacy-preserving AI systems. The AI Controls Matrix (AICM) is a comprehensive framework developed by the Cloud Security Alliance (CSA) to help organizations align their AI practices with international standards and regulations. 

Module 5: Building an AI Security Program

This module focuses on building a comprehensive AI security program to protect AI systems (in development and in production) as well as a security program for the underlying multi-cloud / hybrid-cloud solution. NIST SP 800-18 Rev. 2 Developing Security, Privacy, and Cybersecurity Supply Chain Risk Management Plans for Systems outlines the essential components of a System Security Pan (SSP), which documents security requirements for a system and describes the controls in place or planned to meet those requirements.  NIST SP 1800-35 Implementing a Zero Trust Architecture, which includes a discussion on enabling secure authorized access to enterprise resources distributed across on-premises and multiple cloud environments.  Module 5 also includes is a summary of NIST practices for Assessing Risks and Impacts of AI (ARIA) which supports three evaluation levels: model testing, red-teaming, and field testing.

Module 6: AI governance, AI risk management, AI compliance, AI audit  

This module Includes an overview of AI Governance, Compliance and AI Audit requirements. AI governance includes processes, standards and guardrails that help ensure AI systems and tools are safe and ethical. Includes an overview of NIST-AI-600-1, Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile and companion document AI RMF Playbook. The profile helps organizations identify unique risks posed by generative AI and proposes actions for generative AI risk management that best aligns with their goals and priorities. AI compliance refers to the decisions and practices that enable businesses to stay in line with the laws and regulations that govern the use of AI systems. AI audit requirements focus on ensuring transparency, accountability, and compliance in AI systems.

Upon completion of this course, attendees will have an up-to-date understanding of how AI works, AI implementation options, AI threats and vulnerabilities, AI security controls standards, best practices for building an AI security program, and assessing risks assessing AI security risks. The course covers technical security controls applied to AI systems and underlying infrastructure before, during, and after a cyberattack. Finally, administrative security capabilities, including AI governance, risk management, compliance, and audit considerations will be discussed.

Today’s companies develop, deploy, access AI applications and workloads through many computing environments including public cloud, private cloud, multi-cloud, hybrid cloud, and on-premises. These AI implementations and operations involve the risk of one or more cyberattacks that target the AI systems directly (model tampering, agent manipulation, data poisoning, GPU runtime exploits, etc.) or target the underlying infrastructure (public cloud, private cloud, on-premises, etc.) where the AI systems reside. The various development and deployment solutions make securing high-risk AI systems a challenge. A comprehensive AI cybersecurity program should account the various of development / deployment / operations scenarios.

The objective of this class is to help organizations design, develop, build, and manage high-risk AI systems and the underlying cloud, multi-cloud, hybrid cloud, on-premises environments that support AI systems throughout design, development, deployment, and operations. The course deliverables are grouped into six modules which cover key topics related to building a highly effective AI Security Program.

Module 1: What is Artificial Intelligence (AI) and how does AI work?

Includes an overview of Artificial Intelligence (AI) including how AI works (applications and workloads), AI architecture, components, and processes (models, algorithms, workflows). Module 1 includes topics such as AI Models (Generative AI, Large Language Models (LLMs), foundation models), and Multi-Agent Systems (MAS). A review of AI Use Cases across multiple industry sectors is included.

Module 2: AI Cloud Adoption Frameworks (CAFs)

An AI Cloud Adoption Framework (CAF) provides a structured approach to adopting AI solutions effectively and responsibly. It is designed to guide organizations through the process of implementing AI workloads ensuring scalability, security, and operational excellence. Topics include developing, deploying, and securing AI solutions in Microsoft Azure Cloud, Amazon Web Services (AWS), Google Cloud Platform (GCP) and Oracle Cloud Infrastructure (OCI). Deployment models include IaaS (bring your AI), PaaS (build your AI), and SaaS (buy your AI).

Module 3: AI threats and Vulnerabilities

AI Threats include those related to AI models, the data such models are trained and tested on, the third-party components, plug-ins, and libraries utilized in their development, as well as the platform models are hosted on.  Topics include an overview of the FS-ISAC Adversarial AI Framework, MITRE ATLAS (a framework that provides adversary profiles, techniques, and mitigations for securing AI-enabled systems), and OWASP Agentic AI Threats. Module 3 also includes a discussion of AI vulnerabilities including data related vulnerabilities and model related vulnerabilities. Topics include the OWASP Top 10 for LLM Applications (2025) and the OWASP Top 10 for Agentic Applications (2026).

Module 4: AI security controls

Includes an overview of NIST SP 800-218A Secure Software Development Framework (SSDF) for AI, the Google Secure AI Framework (SAIF), the OWASP AI Security and Privacy Guide, and the Cloud Security Alliance AI Controls Matrix (AICM). NIST SP 800-218A provides secure software development practices specifically for generative AI and dual-use foundation models. The Google Secure AI Framework (SAIF) provides guidance for securing AI systems, including the SAIF Risk Self-Assessment to help build and deploy AI systems securely. The OWASP AI Security and Privacy Guide provides clear and actionable insights on designing, creating, testing, and procuring secure and privacy-preserving AI systems. The AI Controls Matrix (AICM) is a comprehensive framework developed by the Cloud Security Alliance (CSA) to help organizations align their AI practices with international standards and regulations. 

Module 5: Building an AI Security Program

This module focuses on building a comprehensive AI security program to protect AI systems (in development and in production) as well as a security program for the underlying multi-cloud / hybrid-cloud solution. NIST SP 800-18 Rev. 2 Developing Security, Privacy, and Cybersecurity Supply Chain Risk Management Plans for Systems outlines the essential components of a System Security Pan (SSP), which documents security requirements for a system and describes the controls in place or planned to meet those requirements.  NIST SP 1800-35 Implementing a Zero Trust Architecture, which includes a discussion on enabling secure authorized access to enterprise resources distributed across on-premises and multiple cloud environments.  Module 5 also includes is a summary of NIST practices for Assessing Risks and Impacts of AI (ARIA) which supports three evaluation levels: model testing, red-teaming, and field testing.

Module 6: AI governance, AI risk management, AI compliance, AI audit  

This module Includes an overview of AI Governance, Compliance and AI Audit requirements. AI governance includes processes, standards and guardrails that help ensure AI systems and tools are safe and ethical. Includes an overview of NIST-AI-600-1, Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile and companion document AI RMF Playbook. The profile helps organizations identify unique risks posed by generative AI and proposes actions for generative AI risk management that best aligns with their goals and priorities. AI compliance refers to the decisions and practices that enable businesses to stay in line with the laws and regulations that govern the use of AI systems. AI audit requirements focus on ensuring transparency, accountability, and compliance in AI systems.