Strengthening Polymorphic Prompt Assembling: Dynamic Separator Generation Against Emerging Prompt Injection Attacks

Abstract

Polymorphic Prompt Assembling (PPA) defends LLM agents against prompt injections by randomly selecting separator pairs from a fixed pool to isolate user input from system instructions. Although effective, static pool reuse exposes a blast-radius vulnerability: once a separator leaks, it can be exploited in future requests. We propose a dynamic per-request separator generation using domain-separated SHA-256 digests keyed on the timestamp, session identifier, and cryptographic nonce. Each assemble

Categories

Framework mappings

Suggested from the entry's categories.

@misc{dorzhiev2026strengthening,
  title = {{Strengthening Polymorphic Prompt Assembling: Dynamic Separator Generation Against Emerging Prompt Injection Attacks}},
  author = {Nima Dorzhiev and Peng Liu},
  year = {2026},
  month = may,
  eprint = {2605.30534},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.30534}
}