Paper Citation Record · LEDGER

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking

As of 7 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2605.28083.

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

pith.paper-citation-record.v1
2605.28083 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T12:59:17.093731Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

38 of 38 outbound references displayed

verified exact6
verified fuzzy0
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch21

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fc7ceb20-6ecd-49f5-be0b-e2c9160cef0b · outbound

This paper cites $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:03:26.144304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2a78f160-4659-4378-a049-5b57e624a28e · outbound

This paper cites RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:03:26.151010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 498cef02-2813-4134-b2bb-49051f7c6c34 · outbound

This paper cites UniVLA: Learning to Act Anywhere with Task-centric Latent Actions.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking UniVLA: Learning to Act Anywhere with Task-centric Latent Actions

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:03:26.143996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fa10045b-f88c-4830-a299-5d08a7327c92 · outbound

This paper cites SAM 3: Segment Anything with Concepts.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking SAM 3: Segment Anything with Concepts

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:03:26.129999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3f93b054-f893-4352-ac2c-3c871bfa823a · outbound

This paper cites IEEE Trans.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking IEEE Trans

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-29T12:59:17.093731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d04067ba-1640-4c3a-bdd0-ff1cd37ef9f3 · outbound

This paper cites PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-06-29T13:03:26.156465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a9f6b117-8132-47f9-bb30-3b16c7d3caf4 · outbound

This paper cites Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T13:03:26.170383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6cd9cb21-8ef3-410c-b33e-4bfe525cb091 · outbound

This paper cites LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:03:26.146749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 05ea4c42-be25-4d29-9e22-5a8cf73f13e9 · outbound

This paper cites State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:03:26.128480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d6d33fe9-773f-4020-a645-e1ee40b9c94d · outbound

This paper cites In: IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking In: IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-29T12:59:17.093731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a819f867-4397-40a5-91ef-4d4ed7fa9392 · outbound

This paper cites In: Agrawal, P., Kroemer, O., Burgard, W.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking In: Agrawal, P., Kroemer, O., Burgard, W

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-29T12:59:17.093731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd61e68e-0a21-4a2d-97dd-3439d074fbf4 · outbound

This paper cites CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling, October 2025.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling, October 2025

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T13:03:26.125067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 33aced77-c7df-4dee-bb7d-8c91acfe6590 · outbound

This paper cites What Matters in Building Vision-Language-Action Models for Generalist Robots.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking What Matters in Building Vision-Language-Action Models for Generalist Robots

Reference 13

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:03:26.136063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 12b193f6-bb27-4c0c-b5c3-d40d47b2ad85 · outbound

This paper cites In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-29T12:59:17.093731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e77dd52-920a-4a3e-8e38-9db4baf3142c · outbound

This paper cites arXiv preprint arXiv:2602.03153 (2026).

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking arXiv preprint arXiv:2602.03153 (2026)

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-06-29T13:03:26.149186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fd7d37ec-a744-42d8-8570-bb0a83e7a31e · outbound

This paper cites In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-29T12:59:17.093731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25fa4325-aed4-4ec1-bb28-4de6ea1acee9 · outbound

This paper cites C., and Jiang, X.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking C., and Jiang, X

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T13:03:26.099322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1f7e54b2-5c03-442c-ad2c-328ff3ff6445 · outbound

This paper cites CoRRabs/2511.10008(2025).

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking CoRRabs/2511.10008(2025)

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-06-29T13:03:26.141674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4110fc12-d0c9-43df-9fc3-95fce95733b7 · outbound

This paper cites In: IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022, Waikoloa, HI, USA, January 3-8, 2022.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking In: IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022, Waikoloa, HI, USA, January 3-8, 2022

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-29T12:59:17.093731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3c7df25-1758-4cca-9961-c9d038ba541b · outbound

This paper cites SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model

Reference 20

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:03:26.167618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1de37412-1137-4574-a3f0-4a9fc0b4b65d · outbound

This paper cites IEEE Trans.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking IEEE Trans

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-29T12:59:17.093731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92d2dcb1-d590-4646-b1a6-cb920da5e538 · outbound

This paper cites In: Tan, J., Toussaint, M., Darvish, K.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking In: Tan, J., Toussaint, M., Darvish, K

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-29T12:59:17.093731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a99d7194-6c86-452c-861a-5d6e400be804 · outbound

This paper cites Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics

Reference 23

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T13:03:26.125632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c64b9e1e-110a-40d6-88d7-871ba93f9a17 · outbound

This paper cites arXiv preprint arXiv:2509.16645 , year=.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking arXiv preprint arXiv:2509.16645 , year=

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-06-29T13:03:26.162323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2fa6e2ea-0a2d-458c-afa2-d152495b6cb7 · outbound

This paper cites DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:03:26.164912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9f588c1a-eefb-43eb-b908-5dd965283d76 · outbound

This paper cites IEEE Robotics Autom.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking IEEE Robotics Autom

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-29T12:59:17.093731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7119245a-6459-46c1-8cd3-b3aec6713b47 · outbound

This paper cites SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models

Reference 27

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:03:26.153788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 54be7d9d-134d-482f-9633-d19fdc544bea · outbound

This paper cites Haochuan.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking Haochuan

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T13:03:26.159449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation eb9c157b-cc45-4e77-9151-9580e2d8ea2a · outbound

This paper cites Zonghuan.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking Zonghuan

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T13:03:26.117531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ee1feb9c-07e3-420a-91a5-3cfc23b3d1ab · outbound

This paper cites In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-29T12:59:17.093731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a426ccf-11ed-4576-8130-dfe77099d848 · outbound

This paper cites Instructvla: Vision-language-action instruction tuning from understanding to manipulation.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking Instructvla: Vision-language-action instruction tuning from understanding to manipulation

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T13:03:26.133774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5a893bc2-8dcd-4692-8405-f5e0beec1d54 · outbound

This paper cites SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning

Reference 32

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:03:26.146106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 95d4a10d-1fe9-4c5e-9af6-59096fdc8d07 · outbound

This paper cites Zhang, W.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking Zhang, W

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T13:03:26.156426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d11a3f9e-194e-420b-afbd-b826e75994fc · outbound

This paper cites In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-29T12:59:17.093731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dc86dc8-6a0a-49b4-ada0-ad68d891336e · outbound

This paper cites arXiv preprint arXiv:2602.00500 (2026).

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking arXiv preprint arXiv:2602.00500 (2026)

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-06-29T13:03:26.151541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fd788293-a181-497c-9838-7ed4afb7e6ac · outbound

This paper cites BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T13:03:26.114953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 44608501-8c98-4b51-8039-d3ebbace07ac · outbound

This paper cites CoRR abs/2510.09269(2025).

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking CoRR abs/2510.09269(2025)

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-06-29T13:03:26.138838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 929c1d63-d8d1-4464-8e70-94a99bc65ddf · outbound

This paper cites ObjectVLA: End-to-End Open-World Object Manipulation Without Demonstration.

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking ObjectVLA: End-to-End Open-World Object Manipulation Without Demonstration

Reference 38

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T13:03:26.158704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

No inbound Pith citation observations are available.