Prompt injection es una técnica adversarial que manipula un modelo de lenguaje colocando instrucciones maliciosas o no previstas en entradas de usuario, documentos, páginas web u otro contenido que el modelo procesa. Puede hacer que el modelo ignore instrucciones previas, revele información restringida, altere salidas o active acciones no autorizadas.
Prompt injection manipulates an LLM's behaviour (for example to alter response style, retrieve hidden or restricted data, or disrupt interactions) by embedding specific instructions within a prompt. This approach exploits the model's tendency to follow instructions within the prompt sequence, even if instructions are unintended or malicious.
Distinguish between Prompt Injection (hijacking model behavior via malicious input) and Jailbreaking (bypassing safety guardrails to produce restricted content). Both are LLM security threats but differ in mechanism and goal.
A side-by-side comparison of Prompt Injection and Data Poisoning. Understand how runtime instruction manipulation differs from attacks on training data or the training process.