Paper Citation Record · LEDGER

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection

As of 17 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 3 inbound Pith citation observations for arXiv:2507.15042.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2507.15042 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:49:00.970194Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T10:44:10.601057Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T20:00:07.849622Z

Reference resolution

37 of 37 outbound references displayed

verified exact2
verified fuzzy12
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5d655d0d-c75d-4cc5-b2dd-dd1bc81bc65a · outbound

This paper cites MS MARCO: A Human Generated MAchine Reading COmprehension Dataset.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection MS MARCO: A Human Generated MAchine Reading COmprehension Dataset

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:56.106561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a9a8c58-d999-40b8-be0d-4ac180811128 · outbound

This paper cites WWW’18 open challenge: Financial opinion mining and question answering.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection WWW’18 open challenge: Financial opinion mining and question answering

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:49:05.144970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a91a3ef5-86b5-4d5b-9afe-b04dcb38cc9e · outbound

This paper cites Fact or Fiction: Verifying Scientific Claims.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Fact or Fiction: Verifying Scientific Claims

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:49:04.846766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8183669c-5363-4780-acc4-f8cdfcc1192f · outbound

This paper cites FEVER: A large-scale dataset for fact extraction and VERification.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection FEVER: A large-scale dataset for fact extraction and VERification

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:49:04.619938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3bdc3bb4-e328-447f-a096-83ebf39b5f17 · outbound

This paper cites SQuAD: 100,000+ questions for machine comprehension of text.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection SQuAD: 100,000+ questions for machine comprehension of text

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:49:04.341382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 32d60f6b-c450-4e6f-ae73-fa52e357ab80 · outbound

This paper cites BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:56.617124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9847514-dc4c-424c-a875-2971cb3b76eb · outbound

This paper cites Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:49:04.046023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 92af87fd-150b-4984-8085-12ff84a97ae4 · outbound

This paper cites Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:49:03.810414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f6818379-ce7c-496d-b0e3-c8dd9fa3f5a5 · outbound

This paper cites Salem, and Ahmed E.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Salem, and Ahmed E

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:49:03.555565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a359d608-5344-4049-ac7d-a401460176e9 · outbound

This paper cites Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:57.081874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 630c11ab-c934-4e03-8fb2-5715dda31ee6 · outbound

This paper cites Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM Manipulation.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM Manipulation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:57.225641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea27f41a-2e62-4e1a-8a1a-c919c5fc8c86 · outbound

This paper cites BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:57.340757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcc68161-d6d3-4a8e-9e44-af07f4c51e9f · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Detecting Language Model Attacks with Perplexity

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:57.497059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55540e38-55c3-47d6-af28-bcc07804aa99 · outbound

This paper cites Robust Safety Classifier Against Jailbreaking Attacks: Adversarial Prompt Shield.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Robust Safety Classifier Against Jailbreaking Attacks: Adversarial Prompt Shield

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:49:03.327394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7e39d900-ffb7-4ff9-9304-3e2b534f6d06 · outbound

This paper cites CtrlRAG: Black-box Adversarial Attacks Based on Masked Lan- guage Models in Retrieval-Augmented Language Generation.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection CtrlRAG: Black-box Adversarial Attacks Based on Masked Lan- guage Models in Retrieval-Augmented Language Generation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:57.797958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 283a017a-c98d-43e1-a8de-d9ec0d9e2f31 · outbound

This paper cites PRADA: Practical Black-box Adversarial Attacks against Neural Ranking Models.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection PRADA: Practical Black-box Adversarial Attacks against Neural Ranking Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:57.903143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e2d89c9-d531-433b-b9e0-93a1b4e3b595 · outbound

This paper cites One Pixel Attack for Fooling Deep Neural Networks.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection One Pixel Attack for Fooling Deep Neural Networks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:58.038712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75787886-0a10-4a7e-81a2-6873fad46b03 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:58.165779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57954197-763d-49be-905e-01ddf0c74363 · outbound

This paper cites Ignore Previous Prompt: Attack Techniques For Language Models.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Ignore Previous Prompt: Attack Techniques For Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:58.294900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7e68571-f96e-4f65-ada3-7426759e29b2 · outbound

This paper cites Automatic and Universal Prompt Injection Attacks against Large Language Models.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Automatic and Universal Prompt Injection Attacks against Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:58.472087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91050d90-8900-4fe2-a68c-2446cd62a221 · outbound

This paper cites Goal-guided Generative Prompt Injection Attack on Large Language Models.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Goal-guided Generative Prompt Injection Attack on Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:58.642580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd98d08a-721e-473e-af78-e6286c03d56b · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:58.758345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9014105d-ea42-4b63-9c8d-5165e2519b28 · outbound

This paper cites Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-06T15:49:01.623652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5176bed5-3ecb-4986-945d-bf5989dd8968 · outbound

This paper cites TEMPEST: Multi-Turn Jailbreaking of Large Language Models with Tree Search.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection TEMPEST: Multi-Turn Jailbreaking of Large Language Models with Tree Search

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:49:03.044417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1a961bf6-c059-4e95-a1b3-03cbde47ff4e · outbound

This paper cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:59.178419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dd1cd2d-204b-4f1a-858e-be4a3f7284bf · outbound

This paper cites Release Strategies and the Social Impacts of Language Models.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Release Strategies and the Social Impacts of Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:59.296515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31d56b97-da33-4b56-9e70-1cad8fd199f8 · outbound

This paper cites Black-box Adversarial Sample Generation Based on Differential Evolution.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Black-box Adversarial Sample Generation Based on Differential Evolution

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-06T15:49:01.309111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 80dc2c97-6a6f-4fea-a748-0319b4caf0bc · outbound

This paper cites Black-Box Prompt Learning for Pre-trained Language Models.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Black-Box Prompt Learning for Pre-trained Language Models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:49:02.776909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7cd9529c-51c7-47a5-a0f0-311c75fa2bac · outbound

This paper cites Generative Representational Instruction Tuning.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Generative Representational Instruction Tuning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:59.910252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84bbaabe-9546-4bca-8463-bf6be57a6fd4 · outbound

This paper cites Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T15:49:00.035067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbc1b277-a695-4a6e-8905-ad112feabcc2 · outbound

This paper cites Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T15:49:00.202243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba24aec9-af6d-43cc-addf-a10ad5a86257 · outbound

This paper cites an unresolved cited work.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T15:49:00.374240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d87080b-84f7-4314-b8b6-392c0126f2ca · outbound

This paper cites an unresolved cited work.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:49:02.507055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 08737cbd-b2c2-4bd1-89eb-03e6da87eac7 · outbound

This paper cites The Probabilistic Relevance Framework: BM25 and Beyond.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection The Probabilistic Relevance Framework: BM25 and Beyond

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:49:02.322604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fc70a480-734b-4b62-a382-fd83cec2d94f · outbound

This paper cites Download to CSV.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Download to CSV

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:49:02.064640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6d6ba860-845d-409d-b954-ada883c11048 · outbound

This paper cites an unresolved cited work.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection Unresolved cited work

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-06T15:49:00.794927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fb4155e-17e1-42f1-a4aa-c79b8b5123de · outbound

This paper cites EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers.

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:59.538886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 349d7963-e035-454b-a5f8-dcefb9cfe494 · inbound

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain cites this paper.

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-05T10:44:10.601057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a5047a3-ee61-4305-8648-5807f6b954a8 · inbound

Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems cites this paper.

Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:28:59.112223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a06c6220-4bae-4214-864c-7ec085aefb4f · inbound

Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems cites this paper.

Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-07-04T20:00:07.851452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.