InjectGuard-RAG: Lightweight Defence Against Indirect Prompt Injection in Retrieval-Augmented Small-LLM Agents
- 9 October 2026
- book chapter
- Published by Springer Nature
- p. 56-69
Abstract
No abstract availableKeywords
This publication has 11 references indexed in Scilit:
- Benchmarking and Defending against Indirect Prompt Injection Attacks on Large Language Models2025
- Qwen2.5 Technical ReportarXiv, 2025
- Defending against Indirect Prompt Injection by Instruction Detection2025
- Can Indirect Prompt Injection Attacks Be Detected and Removed?2025
- Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection2023
- Transformers: State-of-the-Art Natural Language Processing2020
- Dense Passage Retrieval for Open-Domain Question Answering2020
- Compositional Semantic Parsing on Semi-Structured Tables2015
- The Probabilistic Relevance Framework: BM25 and BeyondFoundations and Trends® in Information Retrieval, 2009
- An Introduction to the Bootstrap1994