Pith. sign in

Paper Citation Record · LEDGER

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

As of 7 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 16 inbound Pith citation observations for arXiv:2505.16640.

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

pith.paper-citation-record.v1
2505.16640 v1

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:04:01.363663Z

measured 65 of 65 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 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T00:41:30.013412Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

49 of 49 outbound references displayed

  • verified exact0
  • verified fuzzy17
  • unresolved32
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation bcd4ab95-aa11-431d-8cda-622ee9854b89 · outbound

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

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:57.978563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:57.978563Z digest=sha256:05cd9687a7604074d138162f7b70df5be154b2defd9dd85a24bcf8001741fb61

Observation 0da2bfcf-eea7-4170-ac2a-cc5786227889 · outbound

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

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:58.041901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:58.041901Z digest=sha256:453bf432bc8c21bfca1fa1bd93f99b8f70975644f152c84b6983d86e7d6bdb71

Observation caf71072-ee0c-47d9-b2ed-9d727d5ea4dc · outbound

This paper cites PaLI-X: On Scaling up a Multilingual Vision and Language Model.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization PaLI-X: On Scaling up a Multilingual Vision and Language Model

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:58.109664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:58.109664Z digest=sha256:2ddb1944c37553513c9d7229a9147c65d25cf5467ddb4d413242ab186c23250d

Observation d6f1e72d-c833-452f-9469-6cc5f7bd23a6 · outbound

This paper cites Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:58.176671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:58.176671Z digest=sha256:21a5781869fa2e505eb10b4644a4b47755813e29ce7f830cf64fb1ea4df5e8cd

Observation 1876874c-b6bf-4318-9732-b2ae36fe931b · outbound

This paper cites Manipulation facing threats: Evaluating physical vulnerabilities in end-to-end vision language action models, 2024.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Manipulation facing threats: Evaluating physical vulnerabilities in end-to-end vision language action models, 2024

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:58.256301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:58.256301Z digest=sha256:9077486d9006bc76d8776064873d15aa1d08abfcd4061977bdead650c87b21a8

Observation 8dad1db0-5b45-49d9-9e85-76110536429b · outbound

This paper cites Open X-Embodiment: Robotic Learning Datasets and RT-X Models.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Open X-Embodiment: Robotic Learning Datasets and RT-X Models

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:58.346357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:58.346357Z digest=sha256:9027589a0c0ca917f3832464a05fa079620b33b67ae8a2a050e9f8901c158cca

Observation b8759b5b-c83c-4f82-b525-f719cab5894d · outbound

This paper cites PaLM-E: An Embodied Multimodal Language Model.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization PaLM-E: An Embodied Multimodal Language Model

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:58.461263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:58.461263Z digest=sha256:851514403b9686dad01c65a7cbe589bed0761d6041c390744ece04917939638c

Observation 5d5141ef-26ee-4ae7-867e-9ef64731601a · outbound

This paper cites Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:58.528602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:58.528602Z digest=sha256:361f32c4e058e88afbd79218b011e5c94544e0326c793aafd868afa5e42466b9

Observation fa4830ef-b66a-4cd3-8da9-0cd4010c3092 · outbound

This paper cites RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:58.569221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:58.569221Z digest=sha256:4f983f2620a61d6a9fda4a29a838ca8984ed4c4fa37c3bb351006db2d33603a0

Observation 700e6b9b-3c97-4f82-b910-fe39f8679dfb · outbound

This paper cites Towards artificial general intelligence via a multimodal foundation model.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Towards artificial general intelligence via a multimodal foundation model

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:05.110305Z

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.

source=pdf_text observed=2026-08-07T15:03:58.611596Z digest=sha256:43c73ac8dbb7c9274ab196f163068825ff09caf77cf345dc761aa8a8c40703aa

Observation 1e9a8a95-a170-49b1-b0d3-a81e517bf936 · outbound

This paper cites Foundation models in robotics: 11 Applications, challenges, and the future.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Foundation models in robotics: 11 Applications, challenges, and the future

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:04.960375Z

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.

source=pdf_text observed=2026-08-07T15:03:58.664521Z digest=sha256:60b6a2272ed9c911e30606a512e3e4b39d5eb21b7c1dd02a700515a91276832f

Observation 1babccfb-e2e0-42ae-8095-26a5f72b24e7 · outbound

This paper cites Robustness of learning from task instructions, 2023.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Robustness of learning from task instructions, 2023

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:04.769333Z

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.

source=pdf_text observed=2026-08-07T15:03:58.731475Z digest=sha256:b544dd4df0b411f6c263fb4d3fa771e93aa80a4c638b12dca62f57da2bdd089b

Observation 7c544824-a1e1-437e-8832-4d7414e69c4c · outbound

This paper cites Badnets: Evaluating backdooring attacks on deep neural networks.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Badnets: Evaluating backdooring attacks on deep neural networks

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:58.824022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:58.824022Z digest=sha256:704c9019ab2b829e4de98b797d61dec0e9cbc857bb4b34923f6c4cac35e0e8ee

Observation 415a7332-e1c7-4c9e-bba3-8a5e67b1e9b3 · outbound

This paper cites Task-oriented Robotic Manipulation with Vision Language Models.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Task-oriented Robotic Manipulation with Vision Language Models

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:58.874940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:58.874940Z digest=sha256:3441be4291c6ad9fc0d0059a2b3c1f4e9cd39355f3e2b33ab87d0d54c5f8f2f8

Observation 0900040f-a961-4724-a701-f732cf3c5436 · outbound

This paper cites Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:58.912326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:58.912326Z digest=sha256:2c99e7db18cab692fc5213f3302fc01de49f5c6ae2d348201a0168223b3ca553

Observation 34ba4f44-e389-4a18-b088-ed238258cc45 · outbound

This paper cites The franka emika robot: A reference platform for robotics research and education.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization The franka emika robot: A reference platform for robotics research and education

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:04.539478Z

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.

source=pdf_text observed=2026-08-07T15:03:59.005600Z digest=sha256:53ff468d4cfffe5b5d135d75a2de2a1e46e5a05608949c63551d309a552c89ff

Observation 57c5ae31-779c-4aaa-8a3c-dd2ea56b6545 · outbound

This paper cites OpenVLA: An Open-Source Vision-Language-Action Model.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization OpenVLA: An Open-Source Vision-Language-Action Model

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:59.101453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:59.101453Z digest=sha256:3ad74312b0e6337d2be6f8806ffa0046702e9f4f8c81f3e401f4f953452e5f9f

Observation 524a9c13-ddf4-4caa-905b-d93d6a0c7822 · outbound

This paper cites Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:59.150301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:59.150301Z digest=sha256:989ebb9391ad270616aaed328d9b4e598a8687fd13fd840554bc4ce6d21027c8

Observation 1b16272f-66ac-4e50-a783-e906c8945fd4 · outbound

This paper cites Vision-Language Foundation Models as Effective Robot Imitators.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Vision-Language Foundation Models as Effective Robot Imitators

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:59.182171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:59.182171Z digest=sha256:ea3c3d6a6229d9ae7f30b88b10a43f137e232ec1241a3eebdbc3b73e55c97a75

Observation 39a6566d-fffd-4e5d-a300-6cddec5e9fe4 · outbound

This paper cites Backdoor learning: A survey.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Backdoor learning: A survey

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:04.369314Z

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.

source=pdf_text observed=2026-08-07T15:03:59.262720Z digest=sha256:82b31c366f2b973b7d93a94592c191a28704ccf95ac07d0e09e5a1ff0db54f48

Observation 9bacaf4a-2350-44d8-966c-dc4cb939dd20 · outbound

This paper cites Vl-trojan: Multimodal instruction backdoor attacks against autoregressive visual language models.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Vl-trojan: Multimodal instruction backdoor attacks against autoregressive visual language models

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:04.201840Z

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.

source=pdf_text observed=2026-08-07T15:03:59.330611Z digest=sha256:bb26d7457682918850dea5cf79364a903d8bc3ea5c97c298d7eebd04d1891f8c

Observation 615a5c13-2769-45a7-90b7-6efda48fc19f · outbound

This paper cites Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:59.401319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:59.401319Z digest=sha256:978dc0666b202c3cbf8cf62d5aab9a67d1a45adb8b4303aa783d7de7fb939a37

Observation fa7bef9c-947b-4452-8b7a-787d949aa26a · outbound

This paper cites Flow Matching for Generative Modeling.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Flow Matching for Generative Modeling

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:59.489710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:59.489710Z digest=sha256:c09ebb09499b49f743bde5865849a7b3137ec5728ce127f3361fdf1a57c626f1

Observation 2f3c0a21-023d-421b-a14a-80048aff993f · outbound

This paper cites Libero: Benchmarking knowledge transfer for lifelong robot learning.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Libero: Benchmarking knowledge transfer for lifelong robot learning

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:59.574527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:59.574527Z digest=sha256:5638262940908df8d54e1b8cdf2342dbb6adcaa2b87b6af1c43d994c9ce24f4b

Observation dc243864-cd91-4efc-9c81-290fc99b70c8 · outbound

This paper cites A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:59.647228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:59.647228Z digest=sha256:f7ca7a4750600bd80b45f5050c96006052a819503bf48b6ce86248e30ef3ff7b

Observation 3269f884-48f7-41ae-ac89-246019cf1dac · outbound

This paper cites Robomamba: Efficient vision- language-action model for robotic reasoning and manipulation.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Robomamba: Efficient vision- language-action model for robotic reasoning and manipulation

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:59.707899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:59.707899Z digest=sha256:8b3db7c8eb7db78fb78205317363409df3f6430f1b20ca52a16eea8fddc33c2c

Observation ec1ad98f-36f4-4d05-bb88-d24723940128 · outbound

This paper cites Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:59.747451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:59.747451Z digest=sha256:09d5e385000660727153c68d7314c5013ca2499c4d5a1b3b204679af1beb1787

Observation e8caa19c-53de-4456-8fd3-a3b8c322e301 · outbound

This paper cites Friendly noise against adversarial noise: a powerful defense against data poisoning attack.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Friendly noise against adversarial noise: a powerful defense against data poisoning attack

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:04.080009Z

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.

source=pdf_text observed=2026-08-07T15:03:59.788553Z digest=sha256:bca2eee5731782842ff20b369f56320786c158583f2e6035c32df2e21e38cf00

Observation c7dbf271-07ba-4189-9537-d477baeae198 · outbound

This paper cites Safety Alignment for Vision Language Models.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Safety Alignment for Vision Language Models

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:59.863053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:59.863053Z digest=sha256:8da9db1a843f6adbb324f25165e72f5718daf44a4b70713af6cd1d6697a79be8

Observation ac2637ee-58ea-4bbd-8dc2-b760e3c7c66d · outbound

This paper cites Trojvlm: Backdoor attack against vision language models.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Trojvlm: Backdoor attack against vision language models

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:03.855423Z

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.

source=pdf_text observed=2026-08-07T15:03:59.929180Z digest=sha256:ed2726570dff722fb2d037d5d7fc698adba917f6b0bcc977e9f605271433e6fb

Observation f2704314-95ca-42b1-9d9c-5ad8d84bda0d · outbound

This paper cites A survey on vision-language-action models for embodied ai, 2025.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization A survey on vision-language-action models for embodied ai, 2025

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:03.608176Z

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.

source=pdf_text observed=2026-08-07T15:04:00.015562Z digest=sha256:ef48cb4b084a37692f2ec7a43d5834d60a8e1464df7845b4de66735dade0ee55

Observation ba2fa290-d44a-49bc-aab9-5a80cbf82ff6 · outbound

This paper cites Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T15:04:00.079070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:04:00.079070Z digest=sha256:9b9947954c4d0bba7ffa6e01f343f4cde3f4d04bdff48ba729d342af047ca88f

Observation 60cc8b52-68a4-4666-9617-aa661226dc9e · outbound

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

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T15:04:00.141487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:04:00.141487Z digest=sha256:b9a429e69d859e73991b6c79aac63bc5704b51bb16c752f6f4d31545e70b9770

Observation cbdcede5-0c6f-473b-a374-a3c41c6ad53a · outbound

This paper cites Certified defenses for data poisoning attacks.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Certified defenses for data poisoning attacks

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:03.348852Z

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.

source=pdf_text observed=2026-08-07T15:04:00.216614Z digest=sha256:aebcbc31d328e4196186b3ecf556bf4d56594222fa7871416b5ab23c37953a99

Observation b4baf0c2-5b84-42fa-bdc9-284192defb98 · outbound

This paper cites Octo: An Open-Source Generalist Robot Policy.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Octo: An Open-Source Generalist Robot Policy

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T15:04:00.287943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:04:00.287943Z digest=sha256:f9877a9282975532248a52ad4e2c4f93da9d7638488cffcd11fd21ca5c434529

Observation e2bb5bd9-fa9b-417b-9d4d-5bdc2155af29 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T15:04:00.372988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:04:00.372988Z digest=sha256:5c5a72161c503389564457f710db0704e9ef04d3a45545e66e851e6b2e1c9171

Observation 5bc2d187-336b-479d-bbe8-a09b8aaa988f · outbound

This paper cites Exploring the adversarial vulnerabilities of vision-language-action models in robotics, 2025.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Exploring the adversarial vulnerabilities of vision-language-action models in robotics, 2025

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:03.176163Z

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.

source=pdf_text observed=2026-08-07T15:04:00.454391Z digest=sha256:0e077e80cc82ea9efaa1e5aa808f45952a9664bb5b33f70cbf7ab325bfd7f7bf

Observation 3b51d84d-c8a8-459e-953b-640e488347c7 · outbound

This paper cites Invisible black-box backdoor attack against deep cross-modal hashing retrieval.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Invisible black-box backdoor attack against deep cross-modal hashing retrieval

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:02.959518Z

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.

source=pdf_text observed=2026-08-07T15:04:00.542534Z digest=sha256:40194e968f679e5d7f07ce93126c89102e33ea8c403b2234faf5d983e3700231

Observation e6a0e3b1-ca48-4bdf-94ea-3d618716c3cf · outbound

This paper cites Trojanrobot: Physical-world backdoor attacks against vlm-based robotic manipulation.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Trojanrobot: Physical-world backdoor attacks against vlm-based robotic manipulation

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T15:04:00.592104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:04:00.592104Z digest=sha256:b27c4f59bf373684c930ca56401d58dfa53d0b225a2cfdfcc55c9405d60d776b

Observation 391293fe-2ed3-40e4-a08e-054d6f949b27 · outbound

This paper cites InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-07T15:04:00.652092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:04:00.652092Z digest=sha256:35018f001067a87cb75187122ef5ed2ff72e3b3c8226460235a7f04560a65d8d

Observation 4cd00f41-373c-4196-b055-82c48e1cd5e2 · outbound

This paper cites Adversarial attacks on multimodal agents.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Adversarial attacks on multimodal agents

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:02.738757Z

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.

source=pdf_text observed=2026-08-07T15:04:00.724979Z digest=sha256:ac2bab794ffffae4ec6183a8dd3aea58e04e820f63949c39b4d2558d5003ba8f

Observation d82ac1d1-7e89-4d3d-98e7-8fdd42d13fa1 · outbound

This paper cites Dissecting Adversarial Robustness of Multimodal LM Agents.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Dissecting Adversarial Robustness of Multimodal LM Agents

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T15:04:00.833689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:04:00.833689Z digest=sha256:4e644e879601fe500e4020b56a36eb1ca12f6b73f40cf8f69c8021d498474f6a

Observation 93a583b2-3863-44a0-a7a1-5a71a206e686 · outbound

This paper cites Adversarial t-shirt! evading person detectors in a physical world,.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Adversarial t-shirt! evading person detectors in a physical world,

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:02.533337Z

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.

source=pdf_text observed=2026-08-07T15:04:00.927104Z digest=sha256:092d8197a217ae8bff6fd0d25956891551e12424b0e8fb3cec27f1eb28d99db6

Observation 0772a19f-d6a7-4ed8-9e35-e47d5d8c28e8 · outbound

This paper cites Compression-resistant backdoor attack against deep neural networks.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Compression-resistant backdoor attack against deep neural networks

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:02.340481Z

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.

source=pdf_text observed=2026-08-07T15:04:01.030790Z digest=sha256:b721348902608eb607f3666d8806824be2ee80004fa59f8462d7f47b8e674d29

Observation 247a933f-e852-4bce-9e46-a762242dacaf · outbound

This paper cites Visual Adversarial Attack on Vision-Language Models for Autonomous Driving.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Visual Adversarial Attack on Vision-Language Models for Autonomous Driving

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T15:04:01.105850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:04:01.105850Z digest=sha256:941cf4276e4dd95ff715164b1d1d55b7a58ee24dfee11fbdf57f9a61f348d342

Observation 9fbc2bca-cdcd-453c-87f9-3ff02b1be280 · outbound

This paper cites Gadei: On scale-up training as a service for deep learning.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Gadei: On scale-up training as a service for deep learning

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:02.122146Z

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.

source=pdf_text observed=2026-08-07T15:04:01.184490Z digest=sha256:17c10173a56c2b92a56797599e773e36462c4e48da7820a110cac58b5179a4a9

Observation 672997b2-8d01-46af-b5d2-e2b5ead04af4 · outbound

This paper cites Badcm: Invisible backdoor attack against cross-modal learning.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Badcm: Invisible backdoor attack against cross-modal learning

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:04:01.886203Z

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.

source=pdf_text observed=2026-08-07T15:04:01.262629Z digest=sha256:dc4afc5a1a137133fe2a633537b602286441b56d07af5e2b3570f038dd8272bd

Observation b9b58612-b4bb-4b69-a49d-d0ceda8543f4 · outbound

This paper cites Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-07T15:04:01.363663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:04:01.363663Z digest=sha256:921dc6cc7ca34a76b88f3d45baed2e5d6c92136e4e647064bbc98990907b0429

Observation ce99ff9e-fb9f-4503-8784-e1aa91e03ff7 · outbound

This paper cites Adversarial T-shirt! Evading Person Detectors in A Physical World.

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Adversarial T-shirt! Evading Person Detectors in A Physical World

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-07T15:04:00.985364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:04:00.985364Z digest=sha256:3165fb0d6951b110e56a4156ec02e0b16d91fd974f2d86cae99b8c2dcfa2d689

Pith citing papers

Observation 5c633738-e24e-4bed-a8b9-d4bf043d77e8 · inbound

ANNIE: Be Careful of Your Robots cites this paper.

ANNIE: Be Careful of Your Robots BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 96

Resolution
unresolved
no resolver link, observed 2026-08-05T11:00:38.344567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T11:00:38.344567Z digest=sha256:7ac8018edacb90d506e9e5eb16ab7a3c1fa1c37ac7b48230f29b3554f57545dc

Observation 8445cced-2873-4095-b6c0-17dfe7baeed9 · inbound

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

State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-03T12:18:22.784748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T12:18:22.784748Z digest=sha256:043a70684939c628d94079702761702880710239dd516574d5cadcac8e9a4fc8

Observation 2ddeba9e-d2a1-4461-b893-8df29db754f0 · inbound

When control meets large language models: From words to dynamics cites this paper.

When control meets large language models: From words to dynamics BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 209

Resolution
verified exact
arxiv_id, observed 2026-05-21T14:54:13.088768Z

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.

source=pdf_text observed=2026-05-21T14:52:44.632671Z digest=sha256:7daedceeed81afa99e7cd9c8a8e4265d013c764b7a29600ac44c8dfda491c5e8

Observation 4b4aeceb-78b5-4045-838f-0e0af595e582 · inbound

SlowBA: An efficiency backdoor attack towards VLM-based GUI agents cites this paper.

SlowBA: An efficiency backdoor attack towards VLM-based GUI agents BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 71

Resolution
unresolved
no resolver link, observed 2026-07-15T12:42:28.672749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-15T12:42:28.672749Z digest=sha256:a154b87c9e3d610e5ba268f31b3658af0240c6e82ef538fb0ae65fd9534cd170

Observation e87022be-e0b8-4987-a14e-599b551b4c92 · inbound

TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches cites this paper.

TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 19

Resolution
unresolved
no resolver link, observed 2026-07-13T19:50:50.950451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-13T19:50:50.950451Z digest=sha256:3782aa60d2701981ef0121ef8a7b0c692b96907426e6b437323cd01726ca9047

Observation f3a24cca-98f1-4f9b-bf74-c7cb9431a1f3 · inbound

SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models cites this paper.

SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 26

Resolution
verified exact
arxiv_id, observed 2026-05-15T01:08:25.704830Z

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.

source=pdf_text observed=2026-05-15T01:06:42.421062Z digest=sha256:2da3b7580380d336f9a792402c2e6b2772d6aa23b8ff15a17894f2b1c1429921

Observation d5bd4e92-2269-4073-96d1-69c7c13de471 · inbound

FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models cites this paper.

FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 44

Resolution
verified exact
arxiv_id, observed 2026-05-14T22:23:03.896495Z

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.

source=pdf_text observed=2026-05-14T22:20:35.818770Z digest=sha256:c2e13a7d1cab7e37c5a91851d28aa6de5782b6f51263d2f3cac49358fd8e1698

Observation 221b7a16-6038-42fd-9a90-802cc48f4b81 · inbound

TRAP: Tail-aware Ranking Attack for World-Model Planning cites this paper.

TRAP: Tail-aware Ranking Attack for World-Model Planning BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 50

Resolution
verified exact
arxiv_id, observed 2026-05-11T10:56:05.031698Z

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.

source=pdf_text observed=2026-05-10T15:15:45.407680Z digest=sha256:3b25d95590b8099e8f474b0f9af90dca1d365b58f4bfa689a7450ca9757c7269

Observation ac84a3ec-5b62-4b10-9e0c-e41c5fef3c6a · inbound

Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability cites this paper.

Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 157

Resolution
verified exact
arxiv_id, observed 2026-05-11T04:35:56.617959Z

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.

source=pdf_text observed=2026-05-11T01:15:19.239355Z digest=sha256:cae14ec481002187bedfa75e6ecab4e9666a9808b3e09a5bf6336bbc640a0238

Observation 35ecd89a-7daf-4a65-b36a-ee6655a4bc4c · inbound

Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models cites this paper.

Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 22

Resolution
verified exact
arxiv_id, observed 2026-05-12T07:36:36.469829Z

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.

source=pdf_text observed=2026-05-12T02:29:34.973993Z digest=sha256:63268e2c9abfeb2f7c6241f8e1c8ebec085ef2c03f425b28c5cf2d274143e896

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

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

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 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-06-29T12:59:17.093731Z digest=sha256:e2b1ffb57c2d567450f341881f48d0b0f8b210272840fffb5877cdde3965c4dc

Observation e70e0a67-6834-4e9b-bb40-d070aae3053d · inbound

ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving cites this paper.

ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 55

Resolution
verified exact
arxiv_id, observed 2026-06-29T11:13:20.755147Z

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.

source=pdf_text observed=2026-06-29T11:10:46.269185Z digest=sha256:801b324d6e1529618044329a308a778eb309cdc4432b2b8a9090622bd17c9ddb

Observation 700ce834-2bac-42a9-a358-ec7a2c49600f · inbound

Targeting World Models to Compromise Robot Learning Pipelines cites this paper.

Targeting World Models to Compromise Robot Learning Pipelines BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 48

Resolution
verified exact
arxiv_id, observed 2026-06-27T16:41:03.723593Z

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.

source=pdf_text observed=2026-06-27T16:05:01.264700Z digest=sha256:037f2cff94d9250e353a8486f04cb070b59126515664424060c08f22bf8dd6ff

Observation e64dd588-8f01-44fb-b2d0-6c771f528b27 · inbound

!Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics cites this paper.

!Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 18

Resolution
unresolved
no resolver link, observed 2026-07-11T21:22:51.640124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T21:22:51.640124Z digest=sha256:475bb4fdf62f2766cd59d43c46230ad26c8f7e570ec3d2d98f1b0d445b8a3c1e

Observation a1f0309d-e2ca-4514-8d06-6260c49e2391 · inbound

ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency cites this paper.

ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-03T12:25:33.857073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-03T12:25:33.857073Z digest=sha256:c2137580df98a44ea5843894f45e06c43e01421e4870f691d2730d45738e9e3b

Observation a83ab1fa-054d-4420-abac-7bec8235f93e · inbound

VLAGuard: A Framework for Evaluating and Mitigating Physical Attention Hijacking in Vision-Language-Action Robots within Wireless Sensor Networks cites this paper.

VLAGuard: A Framework for Evaluating and Mitigating Physical Attention Hijacking in Vision-Language-Action Robots within Wireless Sensor Networks BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-06T00:41:30.013412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T00:41:30.013412Z digest=sha256:474a4a60ae6dfb5b1d75f3dd83183804f0b1f5da96415be855152f530cb996b2