Research
RAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG Systems
Publication date unknown · Discovered arxiv.org
Page published
Publication date unknown · First observed: 14 Oct 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
RAG-PIBench gives defenders a rigorous, leakage-aware way to evaluate prompt-injection detectors for RAG pipelines, which are increasingly exposed to adversarial instructions hidden in retrieved documents.
RAG-PIBench is a leakage-aware benchmark introduced by researchers from Birzeit University, University of Central Florida, and an independent researcher for detecting prompt-injection attacks embedded in retrieved content of RAG systems. The benchmark contains 4,876 contextual examples across frozen train, validation, and protected-test splits, and the authors compare keyword-based, semantic-reference, TF-IDF, and transformer detectors, with DistilBERT achieving the best protected-test performance (F1=0.896, PR-AUC=0.968).