Red-Teaming Generative AI at Scale: The $14B Hallucination Scenario
About This Session
Topic: Red-Teaming Generative AI at Scale: The $14B Hallucination Scenario
Format requested: 45-minute interactive workshop (talk + hands-on red-team exercise + Q&A)
Track fit: Adversarial AI & Deepfakes; AI Failures and Rogue AI Mitigation; National security implications
Author: Anna R. Dudley
Generative Artificial Intelligence (AI) has crossed from interesting tool to load-bearing infrastructure. Banks use it to draft credit memos. Intelligence shops use it for first-draft assessments. Law firms use it for discovery review. The failures that matter are no longer cosmetic. They are operational, and they cascade.
This 45-minute interactive workshop walks security and risk practitioners through one fully developed adversarial scenario: a confident hallucination, propagated through automated downstream systems, that produces a $14 billion exposure event before any human catches it. Attendees see the failure unfold across three layers and trace which controls would have caught it at each stage.
1. Model output
2. System integration
3. Human review
The methodological backbone is Cross-Validated Red Cell: a substantially rebuilt contrarian technique that combines adversarial Machine Learning (ML), Monte Carlo simulation over evidence, and adversarial-injection modeling to attack AI-assisted analysis where it is structurally vulnerable. It is one of four redesigned Structured Analytic Techniques (SATs) for the generative era all anchored in the Analyst-in-the-Loop AI (AITL) principle: AI surfaces, analyst decides.
Attendees leave with a five-step Monte Carlo red-team protocol they can run on any generative-AI deployment in their organization, a taxonomy of three operational failure modes (Plausible-Sounding Synthesis, Confident Hallucination, Source Traceability Collapse), and a worked artifact that converts model output into something a risk committee can interrogate.
Format requested: 45-minute interactive workshop (talk + hands-on red-team exercise + Q&A)
Track fit: Adversarial AI & Deepfakes; AI Failures and Rogue AI Mitigation; National security implications
Author: Anna R. Dudley
Generative Artificial Intelligence (AI) has crossed from interesting tool to load-bearing infrastructure. Banks use it to draft credit memos. Intelligence shops use it for first-draft assessments. Law firms use it for discovery review. The failures that matter are no longer cosmetic. They are operational, and they cascade.
This 45-minute interactive workshop walks security and risk practitioners through one fully developed adversarial scenario: a confident hallucination, propagated through automated downstream systems, that produces a $14 billion exposure event before any human catches it. Attendees see the failure unfold across three layers and trace which controls would have caught it at each stage.
1. Model output
2. System integration
3. Human review
The methodological backbone is Cross-Validated Red Cell: a substantially rebuilt contrarian technique that combines adversarial Machine Learning (ML), Monte Carlo simulation over evidence, and adversarial-injection modeling to attack AI-assisted analysis where it is structurally vulnerable. It is one of four redesigned Structured Analytic Techniques (SATs) for the generative era all anchored in the Analyst-in-the-Loop AI (AITL) principle: AI surfaces, analyst decides.
Attendees leave with a five-step Monte Carlo red-team protocol they can run on any generative-AI deployment in their organization, a taxonomy of three operational failure modes (Plausible-Sounding Synthesis, Confident Hallucination, Source Traceability Collapse), and a worked artifact that converts model output into something a risk committee can interrogate.
Speaker
Anna Dudley
Principal Advisor for Special Projects - Altamira Corporation
Anna R. Dudley is a former Army Intelligence Officer and Principal Advisor for Special Projects. Her work focuses on bringing analytic-tradecraft discipline to generative-Artificial Intelligence (AI) risk across financial services, intelligence, and public-policy environments. She is the author of the forthcoming book Structured Analytic Techniques (SATs) in a Generative Environment, which redesigns the foundational diagnostic and contrarian SATs.
Her public-accountability work includes the Surveillance Pricing Index (SPX), a 65-company composite scoring framework anchored on Federal Trade Commission (FTC) Section 6(b) supply-chain evidence, and the Data Center Stress Index (DCSI), a county-level infrastructure stress grading tool. She lives and works in the United States.
Her public-accountability work includes the Surveillance Pricing Index (SPX), a 65-company composite scoring framework anchored on Federal Trade Commission (FTC) Section 6(b) supply-chain evidence, and the Data Center Stress Index (DCSI), a county-level infrastructure stress grading tool. She lives and works in the United States.
