Paper Citation Record · LEDGER

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference

As of 7 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2608.01020.

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

pith.paper-citation-record.v1
2608.01020 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T00:42:31.204167Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

39 of 39 outbound references displayed

verified exact2
verified fuzzy27
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 900cffbb-e600-405b-8aad-74454c91c20c · outbound

This paper cites Unveiling the vulnerability of private fine-tuning in split-based frameworks for large language models: A bidirectionally enhanced attack,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Unveiling the vulnerability of private fine-tuning in split-based frameworks for large language models: A bidirectionally enhanced attack,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:36.535555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 84e0f646-4a1b-49e5-98eb-508f98222372 · outbound

This paper cites Language models are injective and hence invertible,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Language models are injective and hence invertible,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T00:42:28.176827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa2d9e2b-9f56-47c0-b295-9c83ff0f1bee · outbound

This paper cites Rep2Text: Decoding Full Text from a Single LLM Token Representation.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Rep2Text: Decoding Full Text from a Single LLM Token Representation

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T00:42:28.276638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b902e04b-11a7-4ddd-bc4e-ec9aafd3e5dd · outbound

This paper cites Inverting visual representations with convolutional networks,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Inverting visual representations with convolutional networks,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:36.267438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2667750d-a3e5-4318-8149-30205dfe0dc6 · outbound

This paper cites Understanding Transformer-based Vision Models through Inversion.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Understanding Transformer-based Vision Models through Inversion

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-06T00:42:31.570046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 735f549d-dd75-458b-92c0-62d145269e18 · outbound

This paper cites Sparse model inversion: efficient inversion of vision transformers for data-free applications,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Sparse model inversion: efficient inversion of vision transformers for data-free applications,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:35.926981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f6e854a5-7f5f-492c-8469-acbc6172cb43 · outbound

This paper cites A survey of attacks on large vi- sion–language models: Resources, advances, and future trends,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference A survey of attacks on large vi- sion–language models: Resources, advances, and future trends,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:35.737572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1a3f8058-e0bf-47b5-bba6-2050b962b7aa · outbound

This paper cites Lvlm-ehub: A comprehensive evalu- ation benchmark for large vision-language models,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Lvlm-ehub: A comprehensive evalu- ation benchmark for large vision-language models,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:35.497375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 80177e8a-cfee-432f-a43c-0cc6e4de778a · outbound

This paper cites A survey of state of the art large vision language models: Benchmark evaluations and challenges,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference A survey of state of the art large vision language models: Benchmark evaluations and challenges,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:35.130269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d852de2e-7fd3-4fff-8250-148d2e8d8edc · outbound

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

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Learning transferable visual models from natural language supervision,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T00:42:28.960540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08f9f9e3-b82a-4755-b98d-3d9ddfa4c970 · outbound

This paper cites Visual instruction tuning,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Visual instruction tuning,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:34.913502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation efda392e-900c-412b-9fdd-6bd72e86a1a9 · outbound

This paper cites Improved baselines with visual instruction tuning,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Improved baselines with visual instruction tuning,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:34.738232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d61176b1-410f-430c-9c6c-7cb4c513f253 · outbound

This paper cites Llava-next: A strong zero- shot video understanding model,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Llava-next: A strong zero- shot video understanding model,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:34.428770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f96fe334-1915-4f38-98d8-dbfb38687328 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T00:42:29.343041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83e09ee6-4ad6-406a-ac70-bf67506bbb05 · outbound

This paper cites Qwen2.5-VL Technical Report.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Qwen2.5-VL Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T00:42:29.392607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72117b07-a724-4c12-9674-f85027c352b1 · outbound

This paper cites Qwen3-VL Technical Report.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Qwen3-VL Technical Report

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T00:42:29.481695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34f7ed36-1561-4f5d-b985-142bdbd60095 · outbound

This paper cites Neurosurgeon: Collaborative intelligence between the cloud and mobile edge,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Neurosurgeon: Collaborative intelligence between the cloud and mobile edge,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:34.298730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 81076eba-15a5-423d-8b3b-8578df105b91 · outbound

This paper cites SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T00:42:29.718307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 264f84ab-b502-4368-af15-4e76d698dbef · outbound

This paper cites Model-distributed inference for large language models at the edge,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Model-distributed inference for large language models at the edge,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:34.154313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 14a26aed-54c7-4df0-b0df-ff009e8dce7d · outbound

This paper cites Petals: Collaborative inference and fine-tuning of large models,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Petals: Collaborative inference and fine-tuning of large models,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:34.005500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e051eccf-6d97-4355-9dea-60e8d4638375 · outbound

This paper cites Understanding deep image represen- tations by inverting them,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Understanding deep image represen- tations by inverting them,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:33.849026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f17ad10a-5f44-445b-83b9-206937aab9e8 · outbound

This paper cites The secret revealer: Generative model- inversion attacks against deep neural networks,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference The secret revealer: Generative model- inversion attacks against deep neural networks,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:33.737298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4f8f7999-204e-4d7b-bb6d-d593d76a2b0d · outbound

This paper cites FaceObfuscator: Defending deep learning-based privacy attacks with gradient descent-resistant features in face recognition,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference FaceObfuscator: Defending deep learning-based privacy attacks with gradient descent-resistant features in face recognition,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:33.593905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ea2cbac1-d24d-4940-a0b9-b488dd64b767 · outbound

This paper cites Gradvit: Gradient inversion of vision transformers,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Gradvit: Gradient inversion of vision transformers,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:33.398543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 20ecf680-2b33-4ed6-9ba5-58b2065abaf7 · outbound

This paper cites What do we learn from inverting CLIP models?.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference What do we learn from inverting CLIP models?

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T00:42:30.330083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3eb97dac-c959-47a5-8b05-88248754acc9 · outbound

This paper cites Information leakage in embedding models,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Information leakage in embedding models,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:33.292469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0ec4ea90-b060-4dbd-8085-093a9ad4b3da · outbound

This paper cites Privacy risks of general-purpose language models,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Privacy risks of general-purpose language models,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:33.100376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 291d7993-2487-4aa9-a383-677cda72c9ea · outbound

This paper cites Extracting prompts by inverting llm outputs,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Extracting prompts by inverting llm outputs,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:32.915084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 89fd303f-6e19-4ca6-a77b-323749c9b2a1 · outbound

This paper cites Text embeddings reveal (almost) as much as text,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Text embeddings reveal (almost) as much as text,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:32.752216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f6c9f2aa-49af-4689-81c4-9b4c8be29a52 · outbound

This paper cites Prompt inversion attack against collab- orative inference of large language models,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Prompt inversion attack against collab- orative inference of large language models,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:32.559352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e045d0aa-a0cc-4a1e-b911-e970037bd5e1 · outbound

This paper cites Caprecover: A cross-modality feature inversion attack framework on vision language models,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Caprecover: A cross-modality feature inversion attack framework on vision language models,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:32.428153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 95269d61-675c-4250-99d6-00b83a49a574 · outbound

This paper cites Do vision-language models leak what they learn? adaptive token-weighted model inversion attacks,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Do vision-language models leak what they learn? adaptive token-weighted model inversion attacks,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:32.306493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 169469fb-ad97-4231-bd1b-02763d6a8e33 · outbound

This paper cites Making the v in vqa matter: Elevating the role of image understanding in visual question answering,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Making the v in vqa matter: Elevating the role of image understanding in visual question answering,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:32.160213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bd800934-0492-401a-ae36-8c78b7a56164 · outbound

This paper cites Deep learning face attributes in the wild,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Deep learning face attributes in the wild,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:32.001261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9081f5d2-4e96-4632-a8bf-25b63ef091da · outbound

This paper cites Automated flower classification over a large number of classes,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Automated flower classification over a large number of classes,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T00:42:31.024444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 621d91d1-d45a-44cb-bec8-c858179f1986 · outbound

This paper cites FEVER: a large-scale dataset for Fact Extraction and VERification.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference FEVER: a large-scale dataset for Fact Extraction and VERification

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T00:42:31.081302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a3a0d31-2469-4134-b019-4dcc80db34ee · outbound

This paper cites Ms marco: A human- generated machine reading comprehension dataset,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Ms marco: A human- generated machine reading comprehension dataset,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:31.903031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a2dfb1fd-8599-4409-90cf-c470c465470f · outbound

This paper cites Anycost gans for interactive image synthesis and editing,.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Anycost gans for interactive image synthesis and editing,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:42:31.776581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation affabe7d-c9bf-431e-8f79-51d24993ea9f · outbound

This paper cites Available: https://arxiv.org/abs/2508.04097.

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Available: https://arxiv.org/abs/2508.04097

Reference 2026

Resolution: verified exact; raw_fallback, observed 2026-08-06T00:42:31.426712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

No inbound Pith citation observations are available.