Author

Abhishek Rai

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

Context-Aware Prompt Injection Detection via Small Language Models in RAG Pipelines: nokast-secureRAG

Nokast-secureRAG is presented, a roughly 0.5B-parameter small language model that acts as a semantic firewall between retrieval and generation, and jointly evaluates the user query and retrieved context, classifying the pair as safe, suspicious, or malicious.

Abhishek Rai · 0 citations