AI Security
How untrusted input can influence an AI system and which authorization boundaries limit whether that influence becomes an action.
Links containing ?t= open the video at a specific second.
Video summary
The ideas to retain
1. An instruction hidden in a document can change what the system does
What breaks when an LLM processes the control plane and the data plane through the same channel. Why indirect injection can be more severe when the system connects untrusted content to…
2. Asking the model to ignore its limits
How attacks push a model past intended restrictions. The difference between an anecdotal bypass and a transferable jailbreak family. The role classifiers, streaming guards and rapid…
3. Keeping a dangerous signal inside the system
What happens when the system learns, remembers or retrieves content it should not treat as trusted. Poisoned RAG stores, agent working memory and persistent backdoors. Why removing…
Next step
