Paper Citation Record · LEDGER

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM

As of 17 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 5 inbound Pith citation observations for arXiv:2505.23828.

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

pith.paper-citation-record.v1
2505.23828 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:21:42.346479Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-14T12:36:44.253836Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T02:59:25.273490Z

Reference resolution

41 of 41 outbound references displayed

verified exact0
verified fuzzy14
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 529c4620-40d3-4113-aa05-3cbafec494d2 · outbound

This paper cites Survey of hallucination in natural language generation,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Survey of hallucination in natural language generation,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:39.392740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b97802ee-5bcb-47ba-bfa2-49aafbe01463 · outbound

This paper cites Transforming healthcare education: Harnessing large language models for frontline health worker capacity building using retrieval-augmented generation,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Transforming healthcare education: Harnessing large language models for frontline health worker capacity building using retrieval-augmented generation,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:45.916794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d02dc5e4-0919-47ab-836c-db2f29384ac5 · outbound

This paper cites Potential for gpt technology to optimize future clinical decision-making using retrieval-augmented generation,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Potential for gpt technology to optimize future clinical decision-making using retrieval-augmented generation,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:45.782414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1a43bf60-b4a0-4512-8d7e-4c1ff5aa71c1 · outbound

This paper cites Chain of reference prompting helps llm to think like a lawyer,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Chain of reference prompting helps llm to think like a lawyer,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:45.637491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 96fab2b7-e261-4f54-a336-4e0a429af734 · outbound

This paper cites AutoLAW: Augmented Legal Reasoning through Legal Precedent Prediction.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM AutoLAW: Augmented Legal Reasoning through Legal Precedent Prediction

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:39.682688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4a79b28-d50b-4070-a3b9-f57923bf5f88 · outbound

This paper cites Mycrunchgpt: A llm assisted framework for scientific machine learn- ing,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Mycrunchgpt: A llm assisted framework for scientific machine learn- ing,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:45.499498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 15d25f49-b42e-4948-b4be-4e726343a13e · outbound

This paper cites An Interdisciplinary Outlook on Large Language Models for Scientific Research.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM An Interdisciplinary Outlook on Large Language Models for Scientific Research

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:39.835999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 983ce030-0c50-4e21-9382-d59b44f52379 · outbound

This paper cites Opportunities for retrieval and tool augmented large language models in scientific facilities,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Opportunities for retrieval and tool augmented large language models in scientific facilities,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:45.273194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6585cc9f-7072-4fe3-a5a7-a27ac79cb5cc · outbound

This paper cites EchoSight: Advancing Visual-Language Models with Wiki Knowledge.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM EchoSight: Advancing Visual-Language Models with Wiki Knowledge

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:39.948489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbf74ff2-eacd-4e67-a4e0-ef15b2f5fb08 · outbound

This paper cites PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:40.020790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc749ad0-d4f3-4c11-bf0d-2d2ea5713ce2 · outbound

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

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:40.107539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1352cddc-bea4-444d-a0c2-ac35e9a1594a · outbound

This paper cites Poisoning Retrieval Corpora by Injecting Adversarial Passages.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Poisoning Retrieval Corpora by Injecting Adversarial Passages

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:40.196536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eeedf574-7b1d-488a-8e1f-a0039365b93b · outbound

This paper cites Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:40.287773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 459ca39b-2e64-4264-b250-6e2dffa39d30 · outbound

This paper cites Phantom: General trigger attacks on retrieval augmented language generation,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Phantom: General trigger attacks on retrieval augmented language generation,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:40.381404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f6563ac-2c47-43e2-bbfc-4c186e0a8660 · outbound

This paper cites Poisoning web- scale training datasets is practical,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Poisoning web- scale training datasets is practical,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:45.000137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation aef7ea52-49d6-47a0-81bf-001741b46f25 · outbound

This paper cites Encyclopedic vqa: Visual questions about detailed properties of fine-grained categories,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Encyclopedic vqa: Visual questions about detailed properties of fine-grained categories,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:44.739950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 261c7fb3-9da8-48e0-95c6-3f92a1fafaf9 · outbound

This paper cites Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:40.614803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e30bd1b3-a759-4cd4-a9d3-9dd081fcc786 · outbound

This paper cites Retrieval- augmented generation for knowledge-intensive nlp tasks,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Retrieval- augmented generation for knowledge-intensive nlp tasks,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:40.709980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce73dec8-e161-4ab4-b654-4674387cdbb6 · outbound

This paper cites Poisoning Attacks against Support Vector Machines.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Poisoning Attacks against Support Vector Machines

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:40.788169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72865569-082e-4de2-9568-17134d9977c3 · outbound

This paper cites Local model poisoning attacks to {Byzantine-Robust} federated learning,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Local model poisoning attacks to {Byzantine-Robust} federated learning,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:40.836736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2824b544-a343-4f15-90ef-f8e6b694bede · outbound

This paper cites Badencoder: Backdoor attacks to pre- trained encoders in self-supervised learning,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Badencoder: Backdoor attacks to pre- trained encoders in self-supervised learning,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:44.456896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d438f0fa-5f3f-4c30-ac65-5e164832ce9d · outbound

This paper cites Defeat: Deep hidden feature backdoor attacks by imperceptible perturbation and latent representation constraints,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Defeat: Deep hidden feature backdoor attacks by imperceptible perturbation and latent representation constraints,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:44.198814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b7b40b90-4768-4756-8bdb-39216befe95b · outbound

This paper cites Kerckhoffs, La cryptographie militaire.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Kerckhoffs, La cryptographie militaire

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:43.983920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 95be1161-39ab-4a86-a697-5a433c51d2a1 · outbound

This paper cites Unsupervised k-means clustering algo- rithm,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Unsupervised k-means clustering algo- rithm,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:43.713481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 33163676-9942-43da-96e7-7883f6a5b377 · outbound

This paper cites EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:41.212978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cdc62a5-b2e4-4b08-b23c-388224f71aa6 · outbound

This paper cites Mistral 7B.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Mistral 7B

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:41.269897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d6d30b7-259a-425d-a565-47e182bd736b · outbound

This paper cites Llama 3 model card,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Llama 3 model card,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:43.537417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fdbc471c-a998-480e-910c-bd41589940d0 · outbound

This paper cites InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:41.389521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baf2abde-d710-425f-982c-621fc65b6b36 · outbound

This paper cites Formalizing and benchmarking prompt injection attacks and defenses,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Formalizing and benchmarking prompt injection attacks and defenses,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:41.456553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b07ae3a4-f922-4f4d-924f-3a1d3288c8dc · outbound

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

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Ignore Previous Prompt: Attack Techniques For Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:41.536354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30aa5610-ab9b-44d7-81eb-f9b685d4f56b · outbound

This paper cites Prompt Injection attack against LLM-integrated Applications.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Prompt Injection attack against LLM-integrated Applications

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:41.598385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 568593c2-1d52-4fde-9d20-11fc2ce3f893 · outbound

This paper cites Not what you’ve signed up for: Compromising real-world llm- integrated applications with indirect prompt injection,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Not what you’ve signed up for: Compromising real-world llm- integrated applications with indirect prompt injection,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:43.350327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5395f5fc-363e-42d1-88a5-201d09c27030 · outbound

This paper cites Learning transferable visual models from natural language supervision,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Learning transferable visual models from natural language supervision,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:41.770586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34bbff10-6a13-4662-91df-064b1288c47a · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:41.845428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 814f94bc-f151-430d-834c-27c9d3bf286b · outbound

This paper cites Theoretically principled trade-off between robustness and accuracy,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Theoretically principled trade-off between robustness and accuracy,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:41.891174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19b04edd-5048-486a-a247-d1d459f40f8a · outbound

This paper cites How Robust is Google's Bard to Adversarial Image Attacks?.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM How Robust is Google's Bard to Adversarial Image Attacks?

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:41.966464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96aade47-d54a-489b-8694-17e91fe211e1 · outbound

This paper cites Mitigating Adversarial Effects Through Randomization.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Mitigating Adversarial Effects Through Randomization

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:42.030726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43290c99-1617-4479-9b40-996ce1ac1c73 · outbound

This paper cites Denoising diffusion probabilistic models,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Denoising diffusion probabilistic models,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:42.113542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c44f82d-a9fa-45a5-aaeb-a7d689c79cf6 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:42.188870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3bef515-93f2-4525-8851-2aceec43d073 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:42.271921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75eae8ed-9459-483a-a4c6-cb844ae05f39 · outbound

This paper cites FlexRAG,.

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM FlexRAG,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:43.142562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

Observation ea248668-5f1a-44d3-b223-564b66d90c86 · inbound

Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models cites this paper.

Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:16:08.022968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cc8e46ee-6eca-402a-9c50-bac5ec6150b8 · inbound

Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving cites this paper.

Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:36:08.954153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f807f4e1-2291-4076-9ca0-51efa30d9a07 · inbound

Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation cites this paper.

Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM

Reference 84

Resolution: verified exact; arxiv_id, observed 2026-05-12T05:31:23.683665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 87f325dc-e554-4200-a2ef-724c9ac6d6da · inbound

VFACamou: View-Fused Adversarial Camouflage for Environment-Adaptive Physical Evasion cites this paper.

VFACamou: View-Fused Adversarial Camouflage for Environment-Adaptive Physical Evasion Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-04T02:59:25.275804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 92160704-b664-48cc-9512-28fbb974dd52 · inbound

Imperceptible and Reversible Adversarial Examples against Vision-Language Models for Privacy Protection cites this paper.

Imperceptible and Reversible Adversarial Examples against Vision-Language Models for Privacy Protection Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-14T12:36:44.253836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.