Generative AI is transforming the security landscape, offering both new attack vectors and innovative defenses in the battle for cognitive security.
This course equips students with the skills to deploy Generative AI in Red and Blue team operations, exploring how adversaries use AI-generated text, voice, and video to manipulate perception, erode trust, and exploit cognitive biases.
Attendees will learn how to...
-
Construct AI-powered scam bots leveraging large language models (LLMs) for high-impact phishing and persuasion campaigns
-
Develop countermeasures like "honeybots"—AI-powered deception detectors designed to neutralize these threats.
-
Understand and build synthetic and manipulated media attacks, including AI generated audio and video deception and AI-enhanced information warfare tactics
-
Understand how these tools can be weaponized to fabricate identities, impersonate trusted figures, and orchestrate social engineering attacks at scale.
-
Master deception and counterdeception frameworks that have been used in military and political contexts.