Why it matters
NDC AI 2025 talk on LLM frontdoors and backdoors, jailbreak techniques, control-token abuse, local model compromise, and how attackers or insiders can manipulate model behavior.
My takeaway: Doors of (AI)pportunity: The Front and Backdoors of LLMs - Kasimir Schulz & Kenneth Yeung is a red-team signal. The practical read is to treat model behavior manipulation, hidden logic, and local-model compromise as testable adversarial paths rather than demo-only jailbreak tricks.