Pinned Loading

1. PoisonedRAG PoisonedRAG Public

   [USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

   Python 254 45

2. PISanitizer PISanitizer Public

   [New Preprint] PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization

   Python 16

3. PIArena PIArena Public

   [To appear in ACL 2026] PIArena: A Platform for Prompt Injection Evaluation

   Python 15 2

4. liu00222/Open-Prompt-Injection liu00222/Open-Prompt-Injection Public

   This repository provides a benchmark for prompt injection attacks and defenses in LLMs

   Python 426 66