practitionerThreat Modeling
Add a second detection layer for LLM attacks
Said by Speaker not identified ·
“It's not like that we have to run another model, but it's, this would be the second layer, which we did on the, which Andra was describing.”
Transcript evidence from Javan Rasokat and Andra Lezza -- When Chatbots Go Rogue - Lessons Learned from Building and Defending LLM Applications.