SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.17840 · 2024

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

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.17840.json · badge: /api/ran/2402.17840.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
zhentingqi/rag-privacy canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
get_dstore_path Ran
ran; our contract draft was wrong, not the code
zhentingqi/rag-privacy/modules/knnlm_backbone.py
pointer only (licence: NONE) · get_code("05520f6527f04bde")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhentingqi/rag-privacy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_index_path Ran
ran; our contract draft was wrong, not the code
zhentingqi/rag-privacy/modules/knnlm_backbone.py
pointer only (licence: NONE) · get_code("918cf1d7f24a77f5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhentingqi/rag-privacy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_json Ran
ran; our contract draft was wrong, not the code
zhentingqi/rag-privacy/utils/helpers.py
pointer only (licence: NONE) · get_code("94371f783375881f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhentingqi/rag-privacy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_txt Ran
ran; our contract draft was wrong, not the code
zhentingqi/rag-privacy/utils/helpers.py
pointer only (licence: NONE) · get_code("adb4ccec2a7a0854")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhentingqi/rag-privacy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

setup_logging Ran
ran; our contract draft was wrong, not the code
zhentingqi/rag-privacy/utils/helpers.py
pointer only (licence: NONE) · get_code("44a120baec5809ce")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhentingqi/rag-privacy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_dstore_path 4 other papers
3 dated earlier, 1 later · 1 only as an assembly brick
1911.00172 (2019-11)
Generalization through Memorization: Nearest Neighbor Language Models
2010.00710 (2020-10)
Nearest Neighbor Machine Translation
2201.12431 (2022-01)
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval
and 1 more not named here
get_index_path 4 other papers
3 dated earlier, 1 later · 1 only as an assembly brick
1911.00172 (2019-11)
Generalization through Memorization: Nearest Neighbor Language Models
2010.00710 (2020-10)
Nearest Neighbor Machine Translation
2201.12431 (2022-01)
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval
and 1 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.17840")
get_code_for_paper("2402.17840")
have("2402.17840")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.17840.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.17840.svg)](https://syntology.ai/paper/2402.17840)

Connect an agent — have() is free.