Paper Citation Record · LEDGER

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models

As of 19 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2607.02819.

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

pith.paper-citation-record.v1
2607.02819 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-12T06:51:47.981280Z

measured 18 of 18 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

18 of 18 outbound references displayed

verified exact0
verified fuzzy0
unresolved17
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation dbd41de3-4dce-4f30-89b3-25ce584ebab8 · outbound

This paper cites Qwen2.5-VL Technical Report.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models Qwen2.5-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13701d61-e2a9-4161-90b1-07c087281f44 · outbound

This paper cites A survey of man in the middle attacks.IEEE communications surveys & tutorials, 2016.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models A survey of man in the middle attacks.IEEE communications surveys & tutorials, 2016

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4198edf6-ccaf-4ec3-9ec3-9000eb436ac4 · outbound

This paper cites Vlmevalkit: An open-source toolkit for evaluating large multi- modality models.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models Vlmevalkit: An open-source toolkit for evaluating large multi- modality models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1d08a01-5161-4dd4-99ec-ce2a8733ba55 · outbound

This paper cites On the Robustness of Split Learning against Adversarial Attacks.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models On the Robustness of Split Learning against Adversarial Attacks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc90b245-fd4b-4251-a84b-0b9cc584451a · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models Explaining and Harnessing Adversarial Examples

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00839f20-6653-4b45-aec9-1f27d19caabd · outbound

This paper cites Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a37f00d-ad71-43f8-99d6-5fe879ae7d4f · outbound

This paper cites Hyperion: Low-latency ultra-hd video analytics via collaborative vision transformer inference.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models Hyperion: Low-latency ultra-hd video analytics via collaborative vision transformer inference

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 440ba0be-6978-4966-a466-44e1c736b82e · outbound

This paper cites Backdoorvlm: A benchmark for backdoor attacks on vision-language models.arXiv preprint arXiv:2511.18921, 2025.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models Backdoorvlm: A benchmark for backdoor attacks on vision-language models.arXiv preprint arXiv:2511.18921, 2025

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6aef72d9-2cbc-4180-baa8-6be91531c4b0 · outbound

This paper cites Distributed vlms: Efficient vision-language processing through cloud-edge collabo- ration.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models Distributed vlms: Efficient vision-language processing through cloud-edge collabo- ration

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06f97519-dd78-49ec-a3cf-2f48a55bd0ae · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player? InEuropean conference on computer vision, pages 216–233.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models Mmbench: Is your multi-modal model an all-around player? InEuropean conference on computer vision, pages 216–233

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fff846b-1e87-4d8a-9f32-fdf25722dcd2 · outbound

This paper cites Ocrbench: on the hidden mystery of ocr in large multimodal models.Science China Information Sciences, 67(12):220102, 2024.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models Ocrbench: on the hidden mystery of ocr in large multimodal models.Science China Information Sciences, 67(12):220102, 2024

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6608ec5-22a9-4180-b9b0-2ff432585b52 · outbound

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

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models Formalizing and benchmarking prompt injection attacks and defenses

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1016408-3487-4f47-a519-f22d23f5e031 · outbound

This paper cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58ce6770-6ad8-4f14-b6a0-bfe448e71038 · outbound

This paper cites Prompt inference attack on distributed large language model inference frameworks.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models Prompt inference attack on distributed large language model inference frameworks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9df952bb-8095-4e5f-af7e-86a1da53896c · outbound

This paper cites Net- gpt: A llm-empowered man-in-the-middle chatbot for unmanned aerial vehicle.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models Net- gpt: A llm-empowered man-in-the-middle chatbot for unmanned aerial vehicle

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7805e635-4fd8-41d2-8f52-e562fa6dff41 · outbound

This paper cites edgevlm: Cloud-edge collaborative real-time vlm based on context transfer.arXiv preprint arXiv:2508.12638, 2025.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models edgevlm: Cloud-edge collaborative real-time vlm based on context transfer.arXiv preprint arXiv:2508.12638, 2025

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 746fc0ea-f261-4f38-a0a1-7a97b5f82fac · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e14fb2d-6862-4b85-a702-056c58a87ba7 · outbound

This paper cites vision token manipulation attacks on cloud-edge inference of large vision-language models.

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models vision token manipulation attacks on cloud-edge inference of large vision-language models

Reference 18

Resolution: malformed identifier; no resolver link, observed 2026-07-12T06:51:47.981280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.