Ground Floor·43 min
Brent Harrell · Alex Bernier
Explains how LLM applications and agents create red team attack paths, from prompt injection through RAG poisoning to data exfiltration.
aimachine-learningattack+2
DEF CON 34 talks are here: 354 talks, summarized and searchable.
Browse DEF CON 342 talks in the archive.
1–2 of 2 talks
Ground Floor·43 min
Brent Harrell · Alex Bernier
Explains how LLM applications and agents create red team attack paths, from prompt injection through RAG poisoning to data exfiltration.
Ground Floor·17 min
Brent Harrell · Garet Stroup
Presents a capability maturity model that helps red teams gauge readiness, plan growth, and report progress to leadership.