Prompt Injection

An attack that attempts to override an AI system’s intended instructions.

Prompt injection occurs when malicious or untrusted text attempts to change how a model follows its original instructions. The attack may be written directly by a user or hidden inside a webpage, email or retrieved document.

Defences include isolating instructions from data, limiting tool permissions, validating actions and treating external content as untrusted. Prompt wording alone cannot provide complete protection.

Also in

Diffusion Models Small Language Models Retrieval-Augmented Generation Prompt Engineering Context Engineering Few-Shot Learning

JOIN NOW

Begin the first module

It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.

See the curriculum

Join any time · Build AI skills at your pace