EDUCAUSE

Higher education institutions are rapidly deploying AI systems that handle sensitive student data. However, most security teams have never tested them for vulnerabilities. This hands-on Learning Lab equips higher education security professionals with practical skills to assess, defend, and govern AI systems.

Participants execute real attacks against large language models in a controlled cyber range built around higher education scenarios—performing prompt injection, extracting data from RAG systems, and bypassing safety controls. They then implement the defenses that stop these attacks: input validation, output filtering, guardrails, and detection systems.

The lab series concludes with governance integration, mapping technical skills to the NICE Framework AI Security Competency Area (NF-COM-002) for documented workforce outcomes.

Learning Outcomes:

NOTE: You will be asked to complete assignments in between the Learning Lab segments that support the learning outcomes stated below. You will receive feedback and constructive critique from course facilitators.

• Identify how common AI vulnerabilities manifest in higher education contexts such as chatbots, advising tools, and research assistants.
• Execute hands-on attack techniques to understand how adversaries exploit institutional AI systems.
• Apply defensive controls, including input validation, output filtering, and guardrails to protect AI deployments.
• Develop monitoring approaches to detect suspicious AI system behavior and potential misuse.
• Connect technical AI security skills to the NICE Framework for workforce development and documentation.
• Create a repeatable assessment process for evaluating AI systems across your institution.

Higher education institutions are rapidly deploying AI systems that handle sensitive student data. However, most security teams have never tested them for vulnerabilities. This hands-on Learning Lab equips higher education security professionals with practical skills to assess, defend, and govern AI systems.

Participants execute real attacks against large language models in a controlled cyber range built around higher education scenarios—performing prompt injection, extracting data from RAG systems, and bypassing safety controls. They then implement the defenses that stop these attacks: input validation, output filtering, guardrails, and detection systems.

The lab series concludes with governance integration, mapping technical skills to the NICE Framework AI Security Competency Area (NF-COM-002) for documented workforce outcomes.

Learning Outcomes:

NOTE: You will be asked to complete assignments in between the Learning Lab segments that support the learning outcomes stated below. You will receive feedback and constructive critique from course facilitators.

• Identify how common AI vulnerabilities manifest in higher education contexts such as chatbots, advising tools, and research assistants.
• Execute hands-on attack techniques to understand how adversaries exploit institutional AI systems.
• Apply defensive controls, including input validation, output filtering, and guardrails to protect AI deployments.
• Develop monitoring approaches to detect suspicious AI system behavior and potential misuse.
• Connect technical AI security skills to the NICE Framework for workforce development and documentation.
• Create a repeatable assessment process for evaluating AI systems across your institution.

Higher education institutions are rapidly deploying AI systems that handle sensitive student data. However, most security teams have never tested them for vulnerabilities. This hands-on Learning Lab equips higher education security professionals with practical skills to assess, defend, and govern AI systems.

Participants execute real attacks against large language models in a controlled cyber range built around higher education scenarios—performing prompt injection, extracting data from RAG systems, and bypassing safety controls. They then implement the defenses that stop these attacks: input validation, output filtering, guardrails, and detection systems.

The lab series concludes with governance integration, mapping technical skills to the NICE Framework AI Security Competency Area (NF-COM-002) for documented workforce outcomes.

Learning Outcomes:

NOTE: You will be asked to complete assignments in between the Learning Lab segments that support the learning outcomes stated below. You will receive feedback and constructive critique from course facilitators.

• Identify how common AI vulnerabilities manifest in higher education contexts such as chatbots, advising tools, and research assistants.
• Execute hands-on attack techniques to understand how adversaries exploit institutional AI systems.
• Apply defensive controls, including input validation, output filtering, and guardrails to protect AI deployments.
• Develop monitoring approaches to detect suspicious AI system behavior and potential misuse.
• Connect technical AI security skills to the NICE Framework for workforce development and documentation.
• Create a repeatable assessment process for evaluating AI systems across your institution.

The EDUCAUSE Annual Conference connects the best thinkers in higher education technology.

This is THE event where professionals and technology providers from around the world gather to network, share ideas, grow professionally, and discover solutions to today’s challenges. It’s the largest gathering of your peers…people you can relate to, learn from, and stay connected to throughout the year.