Prompt injection
Smuggling instructions into the text an AI model reads so that the model obeys the attacker instead of its operator. OWASP ranks it the top large-language-model risk (LLM01:2025); in this book it appears both as a way attackers jailbreak models and as a way they hijack defenders' AI moderators.
SubscribersExplained in Chapter 12: Attacking the Defenders
More terms
Chapter 8
Get Chapter 8 free
Subscribe and Chapter 8, The Inflection, opens for you on this site. Invite friends and the rest of Part III opens too.
One email to confirm, then an occasional note about the book. Unsubscribe any time.