Rag n' Roll: A Framework to Evaluate Indirect Prompt Manipulation Attacks against RAG-based Applications
Open Access
- 14 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 138-149
Abstract
No abstract availableFunding Information
- European Union’s Horizon 2020 - Tesatable (101019206)
- German Federal Ministry of Education and Research - AIgenCY (16KIS2012)
- SisWiss (16KIS2330)
This publication has 21 references indexed in Scilit:
- The Hidden Threat in Plain Text: Attacking RAG Data Loaders2025
- Traceback of Poisoning Attacks to Retrieval-Augmented Generation2025
- Lost in the Middle: How Language Models Use Long ContextsTransactions of the Association for Computational Linguistics, 2024
- Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection2023
- Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method2023
- Topic-oriented Adversarial Attacks against Black-box Neural Ranking Models2023
- Machine-Generated Text: A Comprehensive Survey of Threat Models and Detection MethodsIEEE Access, 2023
- Order-Disorder2022
- BERT Rankers are Brittle2022
- Natural Questions: A Benchmark for Question Answering ResearchTransactions of the Association for Computational Linguistics, 2019