arXiv AI
RAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG Systems
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 16
RAG-CT: Mitigating Privacy Risks on Retrieval-Augmented Generation Systems via Scanning Prompt Distribution
RAG-CT is a defense mechanism designed to protect Retrieval-Augmented Generation (RAG) systems from leaking personally identifiable information (PII). It works by detecting malicious queries through analysis of entropy and margin distributions, applying a score-based detection method. Experiments across four attack strategies and four baseline defenses on two datasets show that RAG-CT significantly reduces PII leakage while outperforming existing defenses, all without altering the underlying LLM or retriever.
arXiv Computation and Language
Aug 25
Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitution
arXiv:2608.21656v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for combining large language models (LLMs) with external knowledge sources. How...
arXiv Machine Learning
Aug 11
BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes
arXiv:2608. 08027v1 Announce Type: cross Abstract: Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or external data.
arXiv AI
Sep 30
Retrieve, Reproduce, Reveal: Dissecting Retrieval-Augmented Software Vulnerability Detection
arXiv:2609.37669v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is increasingly used to enhance Large Language Model (LLM)-based software vulnerability detection by grounding p...
arXiv AI
Jun 4
Revisiting Vul-RAG: Reproducibility and Replicability of RAG-based Vulnerability Detection with Open-Weight Models
arXiv:2606. 04739v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong potential for automated software vulnerability detection, particularly in retrieval-augmented generation (RAG) settings.
arXiv AI
Sep 15
PIDS-Bench: Evaluating Prompt-Injection Detectors Under Over-Defense, Obfuscation, and Distribution Shift
arXiv:2609.15017v1 Announce Type: cross Abstract: Prompt-injection detectors are typically evaluated using aggregate F1 on in-distribution test data, which offers limited insight into behavior under...