# Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems

arXiv: https://arxiv.org/abs/2402.17840 · HTML: https://mlsanity.com/paper/2402.17840/

## Key facts

- Cited by 76 papers in the map (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 55 of its 84 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

## Builds on (most cited first, 30 of 55)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [Differentially Private Fine-tuning of Language Models](https://mlsanity.com/paper/2110.06500/) (2021)

## Built on by (most cited first, 30 of 76)

- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Unveiling Privacy Risks in LLM Agent Memory](https://mlsanity.com/paper/2502.13172/) (2025)
- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows](https://mlsanity.com/paper/2506.23260/) (2025)
- [Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data](https://mlsanity.com/paper/2406.14773/) (2024)
- [Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy](https://mlsanity.com/paper/2412.04697/) (2024)
- [Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications](https://mlsanity.com/paper/2411.14110/) (2024)
- [Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2502.06872/) (2025)
- [Mask-based Membership Inference Attacks for Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.20142/) (2024)
- [Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents](https://mlsanity.com/paper/2604.02623/) (2026)
- [Prompt Leakage effect and defense strategies for multi-turn LLM interactions](https://mlsanity.com/paper/2404.16251/) (2024)
- [Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors](https://mlsanity.com/paper/2411.01705/) (2024)
- [RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment](https://mlsanity.com/paper/2412.13746/) (2024)
- [Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries](https://mlsanity.com/paper/2505.15420/) (2025)
- [Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases](https://mlsanity.com/paper/2412.18295/) (2024)
- [RAG with Differential Privacy](https://mlsanity.com/paper/2412.19291/) (2024)
- [1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning](https://mlsanity.com/paper/2508.07667/) (2025)
- [Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems](https://mlsanity.com/paper/2601.07072/) (2026)
- [Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs](https://mlsanity.com/paper/2502.10673/) (2025)
- [PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization](https://mlsanity.com/paper/2505.09921/) (2025)
- [Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval](https://mlsanity.com/paper/2503.15548/) (2025)
- [Towards More Realistic Extraction Attacks: An Adversarial Perspective](https://mlsanity.com/paper/2407.02596/) (2024)
- [Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.19101/) (2025)
- [LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures](https://mlsanity.com/paper/2505.01177/) (2025)
- [Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.03098/) (2025)
- [RAG Security and Privacy: Formalizing the Threat Model and Attack Surface](https://mlsanity.com/paper/2509.20324/) (2025)
- [SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2601.03979/) (2026)
- [Estimating Privacy Leakage of Augmented Contextual Knowledge in Language Models](https://mlsanity.com/paper/2410.03026/) (2024)
- [Beyond Data Privacy: New Privacy Risks for Large Language Models](https://mlsanity.com/paper/2509.14278/) (2025)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) improves pre-trained models by incorporating external knowledge at test time to enable customized adaptation. We study the risk of datastore leakage in Retrieval-In-Context RAG Language Models (LMs). We show that an adversary can exploit LMs' instruction-following capabilities to easily extract text data verbatim from the datastore of RAG systems built with instruction-tuned LMs via prompt injection. The vulnerability exists for a wide range of modern LMs that span Llama2, Mistral/Mixtral, Vicuna, SOLAR, WizardLM, Qwen1.5, and Platypus2, and the exploitability exacerbates as the model size scales up. We also study multiple effects of RAG setup on the extractability of data, indicating that following unexpected instructions to regurgitate data can be an outcome of failure in effectively utilizing contexts for modern LMs, and further show that such vulnerability can be greatly mitigated by position bias elimination strategies. Extending our study to production RAG models GPTs, we design an attack that can cause datastore leakage with a 100% success rate on 25 randomly selected customized GPTs with at most 2 queries, and we extract text data verbatim at a rate of 41% from a book of 77,000 words and 3% from a corpus of 1,569,000 words by prompting the GPTs with only 100 queries generated by themselves.