Open access
Aug 2026
D2ANN-RL: Defense-in-Depth ANN-Reinforcement Learning Framework for LLM Chatbot Code Injection Mitigation
A D2ANN-RL framework that integrates input/output sanitization, context isolation, sandboxing, and secure prompt engineering, supported by hybridization of Artificial Neural Network (ANN)–Reinforcement Learning (RL) detection model is introduced.
Victor Omoboye Oluwasegun, O. Falebita, Nabeela Temitayo Adebola et al.
· Scientific Journal of Comput... · 0 citations