Paper Citation Record · LEDGER

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models

As of 8 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 3 inbound Pith citation observations for arXiv:2508.18805.

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

pith.paper-citation-record.v1
2508.18805 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T16:15:28.030708Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T00:20:22.392337Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T19:58:53.653098Z

Reference resolution

40 of 40 outbound references displayed

verified exact3
verified fuzzy20
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 66417da1-300d-47fb-adff-b300f5dc0145 · outbound

This paper cites Qwen2.5-VL Technical Report.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Qwen2.5-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T16:15:27.875237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9ba9218-e8d3-4ba6-975f-e6c0b375d557 · outbound

This paper cites an unresolved cited work.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-05T16:15:28.659515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4b271477-e5ab-4439-a654-36680910b459 · outbound

This paper cites Inducing high energy-latency of large vision-language models with verbose images.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Inducing high energy-latency of large vision-language models with verbose images

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.648037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e76da6fa-9a04-4989-a2fd-5df1dc3459dd · outbound

This paper cites Denial-of-Service Poisoning Attacks against Large Language Models.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Denial-of-Service Poisoning Attacks against Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T16:15:27.888478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e68c029d-50db-49c6-bc2d-01c55ddca40a · outbound

This paper cites Multi-Modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Multi-Modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.636351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ade4f3e8-6422-42d9-8e29-cc6ba4e98f09 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Gemini: A Family of Highly Capable Multimodal Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T16:15:27.895914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1833f7f3-f800-48e6-a5b2-ce44104748fe · outbound

This paper cites Gemma 3 Technical Report.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Gemma 3 Technical Report

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T16:15:27.899695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 773d815f-f944-4954-81fe-0e34b8491381 · outbound

This paper cites Visual Program- ming: Compositional Visual Reasoning Without Training.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Visual Program- ming: Compositional Visual Reasoning Without Training

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.626207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0feebe9e-6ba9-446e-8452-8dc0a534e032 · outbound

This paper cites Fung, Haoyi Qiu, Mingyang Zhou, Shafiq Joty, Shih-Fu Chang, and Heng Ji.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Fung, Haoyi Qiu, Mingyang Zhou, Shafiq Joty, Shih-Fu Chang, and Heng Ji

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.615565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 52dcbe22-e334-4464-890f-9786224efb40 · outbound

This paper cites Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T16:15:27.911200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7974d260-7dd9-457f-9219-4fc1865a000d · outbound

This paper cites Com- binational backdoor attack against customized text-to-image models.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Com- binational backdoor attack against customized text-to-image models

Reference 11

Resolution: verified exact; raw_fallback, observed 2026-08-05T16:15:28.323077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 71cb6ce4-abf0-43bc-ac50-24143492366e · outbound

This paper cites Backdoor Attacks against Image-to-Image Networks.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Backdoor Attacks against Image-to-Image Networks

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-05T16:15:28.242537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4ac1db56-c0a6-4ef1-bee6-bdddc177481a · outbound

This paper cites OverThink: Slowdown Attacks on Reasoning LLMs.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models OverThink: Slowdown Attacks on Reasoning LLMs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T16:15:27.922887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ac24f95-44d8-46ed-9ed9-513f54eaf0e3 · outbound

This paper cites an unresolved cited work.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-05T16:15:28.603969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 202f50d2-a6be-47a9-94e2-ded5239e986f · outbound

This paper cites Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.592376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2c3e5012-5731-442f-8cd5-bb16d8b9b08c · outbound

This paper cites Visual Instruction Tuning.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Visual Instruction Tuning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.580067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e3a5d878-a7ec-40db-9b59-a6939a7aa8ba · outbound

This paper cites an unresolved cited work.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-05T16:15:28.567501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ea27c311-15b6-41c6-a834-84bccffb81b2 · outbound

This paper cites In-Context Watermarks for Large Language Models.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models In-Context Watermarks for Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T16:15:27.941082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54c8fdca-a182-4728-8556-3951a2cc28d2 · outbound

This paper cites The Multi-Modal Fusion in Visual Ques- tion Answering: A Review of Attention Mechanisms.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models The Multi-Modal Fusion in Visual Ques- tion Answering: A Review of Attention Mechanisms

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.556093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cd0998ff-a2ea-4efc-9eb7-2a0d2036ac54 · outbound

This paper cites Towards Deep Learn- ing Models Resistant to Adversarial Attacks.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Towards Deep Learn- ing Models Resistant to Adversarial Attacks

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.543644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation df6f8fe0-6c10-41b3-816c-bac81d27ff1e · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T16:15:27.953861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d40928c3-4d10-4acd-b17b-a04bbd1dafb8 · outbound

This paper cites DocVLM: Make Your VLM an Efficient Reader.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models DocVLM: Make Your VLM an Efficient Reader

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.532205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 22ad3c20-9065-46e1-a5cc-675a7276e3e0 · outbound

This paper cites Gpt-4 technical report.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Gpt-4 technical report

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.521302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 29572df2-eea8-44c1-a95e-db9f89c1f967 · outbound

This paper cites Visual Adver- sarial Examples Jailbreak Aligned Large Language Models.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Visual Adver- sarial Examples Jailbreak Aligned Large Language Models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.508792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 50462e91-78ea-490f-bb1b-73cc427d6f92 · outbound

This paper cites Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.497450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6b45fdf4-dab7-4b83-a7ec-f3cc52f32e27 · outbound

This paper cites Sponge examples: Energy-latency attacks on neural networks.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Sponge examples: Energy-latency attacks on neural networks

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.486262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 052fbb79-45ed-497d-b4a4-bd52aa0f618d · outbound

This paper cites From Show to Tell: A Survey on Deep Learning-Based Image Cap- tioning.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models From Show to Tell: A Survey on Deep Learning-Based Image Cap- tioning

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.474753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0421231f-8917-4f13-aae5-e8f7cabd70f6 · outbound

This paper cites Promising the future, encoding the past: Ai hype and public media imagery.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Promising the future, encoding the past: Ai hype and public media imagery

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.463057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8f8801c8-9336-4d05-83e1-f4ebca31ee5a · outbound

This paper cites VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-05T16:15:28.120950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d8e5356b-2acb-4643-959e-5ce5e86e2890 · outbound

This paper cites MMed-RAG: Versatile Multimodal RAG System for Medi- cal Vision Language Models.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models MMed-RAG: Versatile Multimodal RAG System for Medi- cal Vision Language Models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.450565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0b3a079a-698a-45a6-aa9f-76a8f375d4b1 · outbound

This paper cites MiMo-VL Technical Report.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models MiMo-VL Technical Report

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T16:15:27.996778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f19484a-f4c9-44ca-9026-7e3ea06225e7 · outbound

This paper cites Instruction backdoor attacks against customized {LLMs}.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Instruction backdoor attacks against customized {LLMs}

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.439116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e78822b0-f10b-49ed-8f48-5021a6f17539 · outbound

This paper cites Self-interpreting Adversarial Images.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Self-interpreting Adversarial Images

Reference 33

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T16:15:28.091203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 43f6b059-17f3-46b5-8091-71beb1cc48b2 · outbound

This paper cites Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T16:15:28.008450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdafa1c5-c530-4513-85cb-d8b059f3caab · outbound

This paper cites Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T16:15:28.012224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f605e189-db2c-4ffb-8924-1d98ddceb4c3 · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.426102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ea47f8f4-5471-4494-8591-8c52a16c758e · outbound

This paper cites Fully meets expectations.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Fully meets expectations

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T16:15:28.023552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2071854-248e-4cd0-b17d-14bab787c63b · outbound

This paper cites an unresolved cited work.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-05T16:15:28.396444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fd78be3a-d3e7-4a23-a62c-c9a06c550d61 · outbound

This paper cites answer_correctness_score.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models answer_correctness_score

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.385215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d32e224d-0d2c-4c3b-a747-52e25f3c2087 · outbound

This paper cites Early VLMs, such as BLIP [14], InstructBLIP [2], and MiniGPT-4 [36], introduce image encoders (e.g., Vision Transformers) paired with large language models (LLMs) as decoders.

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models Early VLMs, such as BLIP [14], InstructBLIP [2], and MiniGPT-4 [36], introduce image encoders (e.g., Vision Transformers) paired with large language models (LLMs) as decoders

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:15:28.414561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation c7c86b43-f625-412e-8782-3febfc23e2df · inbound

Overthink-Triggered Slowdown Attacks on LVLM-Based Robotic Systems cites this paper.

Overthink-Triggered Slowdown Attacks on LVLM-Based Robotic Systems Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-07-03T19:58:53.654888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2be21683-8ff4-42d0-974d-f96e98aca235 · inbound

Hiding in Plain Sight: An Effective Physical Adversarial Patch Attack against Visual-Infrared Fused Face Detection cites this paper.

Hiding in Plain Sight: An Effective Physical Adversarial Patch Attack against Visual-Infrared Fused Face Detection Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models

Reference 109

Resolution: unresolved; no resolver link, observed 2026-07-31T23:55:35.016789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d68626e0-fae3-4cee-90fd-af65acdd7ef6 · inbound

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails cites this paper.

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:22.392337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.