D2ANN-RL: Defense-in-Depth ANN-Reinforcement Learning Framework for LLM Chatbot Code Injection Mitigation

Abstract

The growing cybersecurity vulnerabilities in artificial intelligence (AI) service models, particularly Large Language Models (LLMs), highlight code injection as a critical threat to chatbot reliability and safe deployment. On the account that LLMs process inputs as undifferentiated token sequences, they cannot reliably distinguish trusted system prompts from untrusted user inputs. This architectural limitation enables attackers to exploit direct and indirect prompt injection channels, resulting

Categories

Framework mappings

Suggested from the entry's categories.

@article{oluwasegun2026d2annrl,
  title = {{D2ANN-RL: Defense-in-Depth ANN-Reinforcement Learning Framework for LLM Chatbot Code Injection Mitigation}},
  author = {Victor Omoboye Oluwasegun and O. Falebita and N. Adebola and V. Adekunle and D. Uzodinma and Toluhi Michael Lanre and D. Oyekunle and Chima-Duru Goodness Goziechukwu and Ugochukwu Okwudili Matthew},
  year = {2026},
  month = aug,
  journal = {Scientific Journal of Computer Science},
  doi = {10.64539/sjcs.v2i2.2026.506},
  url = {https://www.semanticscholar.org/paper/3213aa8ef5781dfbbcb9a0083de588fa3ae69e42}
}