Paper Citation Record · LEDGER

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 35 inbound Pith citation observations for arXiv:2405.13401.

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

pith.paper-citation-record.v1
2405.13401 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 35 of 35 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:40:41.782598Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

5
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 514df2ea-4f52-4159-bfc8-f3d9a260311b · inbound

Trustworthiness in Retrieval-Augmented Generation Systems: A Survey cites this paper.

Trustworthiness in Retrieval-Augmented Generation Systems: A Survey TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:08:25.744645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5c5b9e95-3bbb-4406-ad7b-4cafa8674c50 · inbound

The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models cites this paper.

The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-12T18:38:43.953861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation deecf3e3-388b-44ef-a699-41ffdf2dd286 · inbound

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining cites this paper.

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T23:32:37.230867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74aa7b08-0d75-4a24-afb7-ca5bfd349f8e · inbound

Towards Data Governance of Frontier AI Models cites this paper.

Towards Data Governance of Frontier AI Models TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T22:06:54.035633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61a22a2f-d0a7-4d27-909c-3ef14b852efc · inbound

Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning Attacks cites this paper.

Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning Attacks TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:21.666209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0ddddb0-8f99-4396-8ca8-00418049887f · inbound

Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models cites this paper.

Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-23T05:12:34.851769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5ac5dd6b-8dd1-4f83-bbd8-90ec25ef1c92 · inbound

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search cites this paper.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T20:57:43.419115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9150a116-41f8-472c-9876-272acad189e7 · inbound

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations cites this paper.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 109

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.466530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6c6f53b-4988-4542-83d8-7f733db50460 · inbound

Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning cites this paper.

Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T16:16:48.185602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1f203df-f4ad-43ae-9ad1-8c54591dac1f · inbound

A Survey of Scaling in Large Language Model Reasoning cites this paper.

A Survey of Scaling in Large Language Model Reasoning TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-22T21:22:08.830637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d56d1dde-ec97-4420-bfca-e7fe0ae8d995 · inbound

Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey cites this paper.

Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-16T11:40:41.782598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 546d763f-71e8-4c7a-bc68-39fa1abf8dcc · inbound

Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation cites this paper.

Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:20.852978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3c8c8fc-2512-4b48-bc12-3ee0e87aa061 · inbound

EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation cites this paper.

EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T21:02:48.160301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6a40ba3-7413-49b3-ba06-8121ceb5ab82 · inbound

Benchmarking Poisoning Attacks against Retrieval-Augmented Generation cites this paper.

Benchmarking Poisoning Attacks against Retrieval-Augmented Generation TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:32:55.989945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 573329f7-b5db-4245-84ef-0fa19187c5be · inbound

Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs cites this paper.

Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T04:15:38.715186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7e2b917-b872-4255-a38a-bd6775584e96 · inbound

AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption cites this paper.

AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-19T00:36:56.349836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9afb61da-6c6e-4e21-9c9e-2fb3924da373 · inbound

Lexical Hints of Accuracy in LLM Reasoning Chains cites this paper.

Lexical Hints of Accuracy in LLM Reasoning Chains TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T18:48:53.336959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 580c21fc-3a13-4587-a63b-4e0d02514d3f · 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 TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T10:44:10.408846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52f58e19-b598-4fc5-9b7f-c088ce4cde3c · inbound

ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented Code Generation cites this paper.

ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented Code Generation TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T21:33:57.184330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d50cc3e5-ea00-46f9-b825-62f7d219fcfd · inbound

LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems cites this paper.

LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T17:46:15.176301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6461955c-14c8-4607-8e74-c3b0accdb8a1 · inbound

Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption cites this paper.

Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-18T05:25:54.399137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c67070a3-5601-4bf4-b672-f3e44962cd36 · inbound

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems cites this paper.

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:31:02.104160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0adc65de-34c5-444f-b7e6-e5cfa54560dd · inbound

Agentic Adversarial Rewriting Exposes Architectural Vulnerabilities in Black-Box NLP Pipelines cites this paper.

Agentic Adversarial Rewriting Exposes Architectural Vulnerabilities in Black-Box NLP Pipelines TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:11:19.748200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e0e68cb9-b5de-4325-a135-b9dcd0d97ab7 · inbound

Green Shielding: A User-Centric Approach Towards Trustworthy AI cites this paper.

Green Shielding: A User-Centric Approach Towards Trustworthy AI TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:56:23.778336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5ab8f3f8-477e-4aa3-aade-dfef19da42c1 · inbound

FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption cites this paper.

FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:16:28.289453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a9cf813f-7f88-450a-bbe4-87e50f770022 · inbound

Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs cites this paper.

Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-06-29T17:13:44.832483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0bc9e2dd-4f50-443e-a123-3a3cb7bfc1cb · inbound

SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning cites this paper.

SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-29T11:53:23.270899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation af8dbe4a-179b-4305-b2be-7e0275532142 · inbound

BraveGuard: From Open-World Threats to Safer Computer-Use Agents cites this paper.

BraveGuard: From Open-World Threats to Safer Computer-Use Agents TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-01T21:26:14.146280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 641b8f36-8a6c-4748-9cee-9e5de5bb8fde · inbound

DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation cites this paper.

DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-01T20:46:13.957247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 870bb34e-ce41-4dcc-b43a-b3f90ecabc0d · 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 TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:28:59.075490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a8184f7e-6bd3-4435-ad9e-3d4b8fecb102 · inbound

Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents cites this paper.

Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T17:50:00.003684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cca8d82b-e845-47f6-a914-abc17b1e63d5 · inbound

PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption cites this paper.

PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T23:47:27.177409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ecf70044-b349-49cf-ac13-259f53e41759 · inbound

Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability cites this paper.

Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-14T12:01:22.824663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7d1a693-bdcf-4ade-90e2-7ff34090adad · inbound

Salience Induction against Multi-Hop RAG Agents: Threat and Defense cites this paper.

Salience Induction against Multi-Hop RAG Agents: Threat and Defense TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:09.423719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d6c2048-c230-4fe9-8743-ffbd40249bbb · inbound

Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study cites this paper.

Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-31T12:10:46.258584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.