Most organizations consume AI rather than build it, which means every security professional now has to treat AI systems as part of the attack surface. This foundational course expects general cybersecurity knowledge and no AI/ML background at all. It sets out what AI and machine-learning systems actually are in security terms, then works through the AI threat landscape by way of MITRE ATLAS, the risks that come with LLM-based applications by way of the OWASP Top 10 for LLM Applications, and the widening attack surface that autonomous AI agents introduce.
Participants tie all of it back to the NIST AI Risk Management Framework and finish with the practical defenses and workforce habits that fold AI into ordinary security work — inventory, input and output filtering, least-privilege tool access, monitoring, and the human review gates that catch what automation misses.
What You Will Learn
- Explain what makes AI/ML systems a security attack surface
- Tell traditional ML, generative AI, LLMs, and AI agents apart
- Find your way around the AI threat landscape using MITRE ATLAS
- Threat-model LLM applications against the OWASP Top 10 for LLM Applications
- Weigh the risks that autonomous AI agents and excessive agency introduce
- Put the NIST AI Risk Management Framework to work (Govern, Map, Measure, Manage)
- Apply baseline AI defenses: inventory, input and output filtering, least-privilege tool access, monitoring, and human review gates
This course is available for "remote" learning and will be available to anyone with access to an internet device with a microphone (this includes most models of computers, tablets). Classes will take place with a "Live" instructor at the date/times listed below.
Upon registration, the instructor will send along additional information about how to log-on and participate in the class.
