SEC536: Adversarial AI - Penetration Testing AI Systems


Experience SANS training through course previews.
Learn MoreLet us help.
Contact usBecome a member for instant access to our free resources.
Sign UpWe're here to help.
Contact UsThe 7 strategies:
The throughline across all seven strategies is a single diagnostic test: before handing a task to AI, ask whether an LLM with search access could produce it in one prompt. If yes, it's commodity work worth doing fast but not worth building an identity around. If no, that task is where a genuine professional moat gets built, and the framework's advice is to protect it, build on it, and document it deliberately rather than letting it happen by accident.
A moat is the knowledge, field experience, and judgment a professional holds that isn't captured in any AI training dataset, making their expertise resistant to AI commoditization, according to SANS Instructor Matt Edmondson's framework "Build Your MOAT."
Ask whether an LLM with access to search could produce the output with a single prompt. If yes, it's commodity work; if no, that task is where differentiated expertise gets built.
One strategy is specializing at the intersections of two or more knowledge domains that few people occupy together, since AI models are typically trained on domains separately and struggle to bridge the gaps between them.
No. The framework recommends using AI to compress the learning curve, not skip it, for example by forming your own analysis first and then comparing your reasoning against AI's output to sharpen judgment.


Launched in 1989 as a cooperative for information security thought leadership, it is SANS’ ongoing mission to empower cybersecurity professionals with the practical skills and knowledge they need to make our world a safer place.
Read more about SANS Institute


















