Question 1

What problem does Polymorphic Prompt Assembling (PPA) address for LLM agents?

Accepted Answer

PPA addresses prompt injection attacks where crafted adversarial inputs manipulate the model to ignore intended instructions. It aims to disrupt attackers’ ability to predict and break the prompt structure.

Question 2

Why do traditional defenses like input filtering and system prompt enforcement struggle?

Accepted Answer

The document explains that these defenses can fail against evolving adaptive strategies, especially when attackers can infer or learn the prompt structure. That predictability makes successful exploitation easier.

Question 3

How does PPA improve security while keeping overhead low?

Accepted Answer

PPA randomly varies the structure and combination/placement of system and user inputs before the LLM processes them. This prevents attackers from reliably predicting the final prompt structure, providing stronger security with near-zero runtime overhead.