Defensive Reverse Engineering of LLM Applications: A Black-Box Framework for Security Risk Scoring and Mitigation

Abstract

Large language model (LLM) applications now combine hidden prompts, retrieval pipelines, memory stores, content filters, tool calls, delegated identities, and downstream automation. Security reviewers are increasingly asked to assess such systems without access to source code, model weights, prompt templates, vector-store configuration, or internal logs. This paper presents D-RELLM, a defensive reverse-engineering framework for black-box security assessment of deployed LLM applications. The fram

Categories

@article{prajapati2026defensive,
  title = {{Defensive Reverse Engineering of LLM Applications: A Black-Box Framework for Security Risk Scoring and Mitigation}},
  author = {Bhavesh B. Prajapati and Bhavya Shah},
  year = {2026},
  month = aug,
  journal = {International journal of computer information systems and industrial management applications},
  doi = {10.70917/ijcisim-2026-4703},
  url = {https://www.semanticscholar.org/paper/28983a3205a8f92c62682310e831f05d4eae8fab}
}