spotlighting

Marking untrusted text in a prompt, by delimiting, interleaving a marker or encoding it, so the model can tell it is data and not instructions.

In more detail

Hines and colleagues at Microsoft showed in 2024 that it lowers indirect injection success a great deal, but not to zero. Use it to make attacks less likely, never as the control that stops damage.

Related terms

Taught in

References

Certification courses