Paper Citation Record · LEDGER

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

As of 9 August 2026, this Paper Citation Record lists 74 of 74 outbound references and 6 inbound Pith citation observations for arXiv:2506.07214.

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

pith.paper-citation-record.v1
2506.07214 v1

Coverage vector

measured 74 of 74 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:45:56.219843Z

measured 80 of 80 standing notices

One-hop event checks from named stored sources.

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

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T21:08:17.981943Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T19:48:57.413143Z

Reference resolution

74 of 74 outbound references displayed

verified exact5
verified fuzzy36
unresolved31
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a6cb0417-934a-49e7-9edb-68ef3a555817 · outbound

This paper cites Improved baselines with visual instruction tuning,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Improved baselines with visual instruction tuning,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.994511Z

Source-reported events for the cited work

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

Observation 00fea122-afc2-4e0e-9a79-f0e56c3796f5 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.029138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 768710b3-4128-4208-b581-6633d4db11d3 · outbound

This paper cites Llama 3.2: Revolutionizing edge ai and vision with open, customizable models,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Llama 3.2: Revolutionizing edge ai and vision with open, customizable models,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.987092Z

Source-reported events for the cited work

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

Observation c135fcf9-1a90-4ee8-bcb1-c9cb72b4bf49 · outbound

This paper cites Backdooring vision- language models with out-of-distribution data,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Backdooring vision- language models with out-of-distribution data,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.979739Z

Source-reported events for the cited work

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

Observation af656723-1504-4f8b-9222-ac6fceacebcb · outbound

This paper cites Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:45:56.655101Z

Source-reported events for the cited work

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

Observation 8fd0ed94-953b-4294-a669-865a17b2ce9f · outbound

This paper cites VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.040880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb648ba0-35e6-4a79-8026-7e7598b424d0 · outbound

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

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Trojvlm: Backdoor attack against vision language models,

Reference 7

Resolution: verified exact; doi, observed 2026-08-07T05:45:56.259423Z

Source-reported events for the cited work

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

Observation bfba5768-c051-45f0-a4b0-bfa87b5bae02 · outbound

This paper cites Shadowcast: Stealthy data poisoning attacks against vision-language models,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Shadowcast: Stealthy data poisoning attacks against vision-language models,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.972248Z

Source-reported events for the cited work

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

Observation ef2d59d7-44e9-4e02-bdb9-f06868991415 · outbound

This paper cites BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.049170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6488e06-11e7-4e7d-b750-d4d667b015a3 · outbound

This paper cites Poisoning and backdooring contrastive learning,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Poisoning and backdooring contrastive learning,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.964662Z

Source-reported events for the cited work

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

Observation eb291362-1dba-4324-939a-6c4eed9132c6 · outbound

This paper cites BadCLM: Backdoor Attack in Clinical Language Models for Electronic Health Records.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation BadCLM: Backdoor Attack in Clinical Language Models for Electronic Health Records

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.060053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d643b54-d96b-4bbc-bf5b-e81d64d4e729 · outbound

This paper cites Badnl: Backdoor attacks against NLP models with semantic-preserving improvements,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Badnl: Backdoor attacks against NLP models with semantic-preserving improvements,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.063013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e18bc35-b50e-4445-982c-5551ffaeb0db · outbound

This paper cites Drivellava: Human-level behavior decisions via vision language model,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Drivellava: Human-level behavior decisions via vision language model,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.948630Z

Source-reported events for the cited work

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

Observation a0f0db94-d0fc-474f-98a3-f1917d5320ad · outbound

This paper cites V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Models.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.068192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f35430a-88b7-4d7a-a17f-a730aea5a817 · outbound

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

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation PaLM-E: An Embodied Multimodal Language Model

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.070868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27e4b751-6c31-4737-b6b3-7cb5d2275871 · outbound

This paper cites RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.073790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88009e1d-8e5f-48af-b396-c6847873649b · outbound

This paper cites Test-Time Backdoor Attacks on Multimodal Large Language Models.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Test-Time Backdoor Attacks on Multimodal Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.076595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9da351e-23e0-4da1-a9b5-d11b06f33829 · outbound

This paper cites Bait: Large language model backdoor scanning by in- verting attack target,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Bait: Large language model backdoor scanning by in- verting attack target,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.941077Z

Source-reported events for the cited work

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

Observation 3dc9d800-54f9-47bd-a093-d40566650eed · outbound

This paper cites Better trigger inversion optimization in backdoor scanning,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Better trigger inversion optimization in backdoor scanning,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.933458Z

Source-reported events for the cited work

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

Observation b6db61e9-aecf-44eb-839d-4d61e53f7d91 · outbound

This paper cites Data Poisoning Attacks Against Multimodal Encoders.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Data Poisoning Attacks Against Multimodal Encoders

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:45:56.599339Z

Source-reported events for the cited work

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

Observation d0d1aff9-c36c-462a-9661-4c09858d7750 · outbound

This paper cites Gpt-4o system card,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Gpt-4o system card,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.925838Z

Source-reported events for the cited work

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

Observation ee415a58-d2af-4620-b7d0-e4b29722c1d3 · outbound

This paper cites Gemini 2.0 flash,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Gemini 2.0 flash,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.918434Z

Source-reported events for the cited work

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

Observation 261ec98c-7004-4ffe-bc27-02b7cd0d7b1c · outbound

This paper cites A Survey on Hallucination in Large Vision-Language Models.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation A Survey on Hallucination in Large Vision-Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.092242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2193722c-be14-4d1a-9fef-be69133f5dc4 · outbound

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

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Learning transferable visual models from natural language supervision,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.095405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5183cfe-608e-42de-8254-5f050d81ab85 · outbound

This paper cites Lora: Low-rank adaptation of large language models,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Lora: Low-rank adaptation of large language models,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.901321Z

Source-reported events for the cited work

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

Observation 0d14e824-d763-4565-a791-8b94747063ef · outbound

This paper cites Backdoor attacks against learning systems,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Backdoor attacks against learning systems,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.887433Z

Source-reported events for the cited work

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

Observation 924b8ed7-7c1b-49b5-ad1f-1ea604261169 · outbound

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

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.109452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5251851-bc3b-4569-b3c5-b0aa2a82d093 · outbound

This paper cites Weight poisoning attacks on pretrained models,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Weight poisoning attacks on pretrained models,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.880660Z

Source-reported events for the cited work

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

Observation b32a1222-9944-40e0-aff8-49a7c8513fef · outbound

This paper cites Available: https://openreview.net/for um?id=nZeVKeeFYf9 3, 6.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Available: https://openreview.net/for um?id=nZeVKeeFYf9 3, 6

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.894243Z

Source-reported events for the cited work

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

Observation 09f7747f-8732-44cc-bb44-a9a81a3398a0 · outbound

This paper cites Hidden killer: Invisible textual backdoor attacks with syntactic trigger,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Hidden killer: Invisible textual backdoor attacks with syntactic trigger,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.866989Z

Source-reported events for the cited work

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

Observation b84b352a-0573-42d3-b453-a71ace2f3fd8 · outbound

This paper cites Mind the style of text! adversarial and backdoor attacks based on text style transfer,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Mind the style of text! adversarial and backdoor attacks based on text style transfer,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.860011Z

Source-reported events for the cited work

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

Observation 7c5cf015-a36d-455c-8fc0-e8d1f7a3b9f4 · outbound

This paper cites Backdoor Pre-trained Models Can Transfer to All.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Backdoor Pre-trained Models Can Transfer to All

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.121769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69c7ab8d-e99f-480c-9944-ce0a40d274d2 · outbound

This paper cites A backdoor attack against lstm-based text classification systems,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation A backdoor attack against lstm-based text classification systems,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.873765Z

Source-reported events for the cited work

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

Observation d4a748be-ca8e-48f7-8d6d-cf51eadc7051 · outbound

This paper cites Lora-as-an-attack! piercing llm safety under the share-and-play scenario,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Lora-as-an-attack! piercing llm safety under the share-and-play scenario,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.852904Z

Source-reported events for the cited work

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

Observation 0f5e6972-07ca-4094-8308-210a46c88f07 · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.129528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd834970-b9e7-4d3f-ac92-8414aee44c0a · outbound

This paper cites Poisoning language models during instruction tuning,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Poisoning language models during instruction tuning,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.846036Z

Source-reported events for the cited work

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

Observation 0297524c-9f8f-4e5b-a3f1-3692d71570c5 · outbound

This paper cites Backdoor pre- trained models can transfer to all,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Backdoor pre- trained models can transfer to all,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.124631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13554ec4-ca22-4ef9-9013-a1475065331a · outbound

This paper cites Backdooring instruction-tuned large language models with virtual prompt injection,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Backdooring instruction-tuned large language models with virtual prompt injection,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.838874Z

Source-reported events for the cited work

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

Observation 325a6572-ecd8-4fb6-853a-a83805baa43a · outbound

This paper cites Backdooring multimodal learn- 15 ing,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Backdooring multimodal learn- 15 ing,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.831910Z

Source-reported events for the cited work

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

Observation 46153329-7c30-45db-a824-f0dbb9571036 · outbound

This paper cites azure-open-dataset,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation azure-open-dataset,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.824901Z

Source-reported events for the cited work

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

Observation d5f5a94d-64c7-4426-be51-ccce25be8610 · outbound

This paper cites Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.134629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20b77c5b-e19f-439c-8517-ec2b6efb34f2 · outbound

This paper cites Visual hallucinations of multi-modal large language models,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Visual hallucinations of multi-modal large language models,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.809992Z

Source-reported events for the cited work

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

Observation 03aea609-f8a5-465a-bd29-24afa8a79559 · outbound

This paper cites Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.153036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b754bf65-e1b6-4b1e-a781-8b9beb442551 · outbound

This paper cites Colorbench: Can vlms see and understand the colorful world? a comprehensive benchmark for color perception, reasoning, and robustness,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Colorbench: Can vlms see and understand the colorful world? a comprehensive benchmark for color perception, reasoning, and robustness,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.155786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a61990d-2610-4f94-935b-08a4f8fca34c · outbound

This paper cites huggingface-dataset,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation huggingface-dataset,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.816881Z

Source-reported events for the cited work

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

Observation bf163804-42f1-4339-8915-b2b139b78604 · outbound

This paper cites Step1X-Edit: A Practical Framework for General Image Editing.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Step1X-Edit: A Practical Framework for General Image Editing

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.160952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e01036b-05ac-4410-b93c-a4cfbc1c5476 · outbound

This paper cites Available: https://arxiv.org/abs/2402.1 4683 4, 13.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Available: https://arxiv.org/abs/2402.1 4683 4, 13

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.802594Z

Source-reported events for the cited work

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

Observation be3cd4ab-8ce9-46b9-b600-89047d23bb88 · outbound

This paper cites Qwen2.5-vl,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Qwen2.5-vl,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.794979Z

Source-reported events for the cited work

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

Observation 181f3c84-8a10-4082-9b19-990952a521f5 · outbound

This paper cites Gemma 3-4b,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Gemma 3-4b,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.787078Z

Source-reported events for the cited work

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

Observation 26d672a1-9399-4cfa-9b28-80baccf2219e · outbound

This paper cites Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.158352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21182d8c-f859-45bc-bd89-190ac3c97ca5 · outbound

This paper cites Qwen2.5-VL Technical Report.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Qwen2.5-VL Technical Report

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.172886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11dbd6c3-9897-4ac3-9064-ecfc134b72b9 · outbound

This paper cites Diffusion model-based image editing: A survey,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Diffusion model-based image editing: A survey,

Reference 53

Resolution: malformed identifier; no resolver link, observed 2026-08-07T05:45:56.163474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0efd13b3-7c03-46a5-9e15-e4a37eef5cc1 · outbound

This paper cites Self-consistency of voting implies majority vote.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Self-consistency of voting implies majority vote

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:45:56.381292Z

Source-reported events for the cited work

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

Observation 4c71b8be-ab86-4859-8903-c3a706ba4fc1 · outbound

This paper cites Llava-1.5,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Llava-1.5,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.771304Z

Source-reported events for the cited work

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

Observation 760e5579-32c2-45be-9344-7e6bf20af0f3 · outbound

This paper cites Gemma 3-12b,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Gemma 3-12b,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.779274Z

Source-reported events for the cited work

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

Observation b1bd4ee8-019a-4b49-8e72-bd7c243664dc · outbound

This paper cites Llama 3.2-vision,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Llama 3.2-vision,

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.755207Z

Source-reported events for the cited work

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

Observation 20332416-ac87-42b8-bf00-9ee0bd41b8dd · outbound

This paper cites Gemma 3 Technical Report.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Gemma 3 Technical Report

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.175491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16f29a1b-9517-4780-a726-f36c3b9e4fa1 · outbound

This paper cites Gqa: A new dataset for real-world visual reasoning and composi- tional question answering,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Gqa: A new dataset for real-world visual reasoning and composi- tional question answering,

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.747536Z

Source-reported events for the cited work

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

Observation 9e098aa4-c64d-4590-a0d8-c0eb3f1ef693 · outbound

This paper cites Llamafactory: Unified efficient fine-tuning of 100+ language models,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Llamafactory: Unified efficient fine-tuning of 100+ language models,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.739346Z

Source-reported events for the cited work

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

Observation d9ffd8b3-11c2-4588-8528-258d3074c987 · outbound

This paper cites Qwen2-vl,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Qwen2-vl,

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.763038Z

Source-reported events for the cited work

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

Observation 5643c838-99ef-457e-a4c4-4af854cfbca7 · outbound

This paper cites Invisible backdoor attack with sample-specific triggers,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Invisible backdoor attack with sample-specific triggers,

Reference 62

Resolution: verified exact; raw_fallback, observed 2026-08-07T05:45:56.364627Z

Source-reported events for the cited work

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

Observation 9910855a-c058-4f3d-9388-ca14f263d480 · outbound

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

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Making the V in VQA matter: Elevating the role of image understanding in visual question answering,

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.188568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb38b32c-6f43-4021-b41f-0722234779f4 · outbound

This paper cites Revisiting backdoor attacks against large vision-language models from domain shift,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Revisiting backdoor attacks against large vision-language models from domain shift,

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.730766Z

Source-reported events for the cited work

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

Observation e4ba4c13-a3cd-4140-8685-2da4ca31a226 · outbound

This paper cites Cl- attack: Textual backdoor attacks via cross-lingual triggers,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Cl- attack: Textual backdoor attacks via cross-lingual triggers,

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.206256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e095e507-a3e2-4e29-8570-d1b6a2f9c7c0 · outbound

This paper cites BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.195950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c35a0bb-f46f-4451-8176-3b1abee99629 · outbound

This paper cites Security Steerability is All You Need.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Security Steerability is All You Need

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.211530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9071bc66-f75a-452b-b435-22fdc62157bc · outbound

This paper cites Mind the style of text! adversarial and backdoor attacks based on text style transfer,.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Mind the style of text! adversarial and backdoor attacks based on text style transfer,

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.201249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 374baade-a7fc-4e4a-8609-d378d609dd23 · outbound

This paper cites LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.217075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01b29d15-f705-4829-be0e-7b83ac537305 · outbound

This paper cites Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.219843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60d9ec34-bc6f-4b60-8150-f58f7bffc2f5 · outbound

This paper cites Fine-Tuning Is All You Need to Mitigate Backdoor Attacks.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Fine-Tuning Is All You Need to Mitigate Backdoor Attacks

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.208799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c83337f1-0912-470d-84b6-9313d3743c0e · outbound

This paper cites A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.214257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0d7e316-d7bb-4af9-96c1-e5fdf505e56d · outbound

This paper cites Available: https://arxiv.org/abs/2103.0 0020 2.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Available: https://arxiv.org/abs/2103.0 0020 2

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.908217Z

Source-reported events for the cited work

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

Observation 0528850e-819c-44ce-b297-7f8443cfa466 · outbound

This paper cites Available: https://openreview.net/for um?id=iC4UHbQ01Mp 1, 2, 3.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Available: https://openreview.net/for um?id=iC4UHbQ01Mp 1, 2, 3

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:45:56.956968Z

Source-reported events for the cited work

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

Observation 33f4305a-204b-424a-9d7d-8d81101f5f0e · outbound

This paper cites Available: https://doi.org/10.1109/CV PR52733.2024.02484 1, 2, 3, 6.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation Available: https://doi.org/10.1109/CV PR52733.2024.02484 1, 2, 3, 6

Reference 2024

Resolution: malformed identifier; no resolver link, observed 2026-08-07T05:45:56.026292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 56f2af8f-f67a-4299-863e-101503cb78bf · inbound

IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding cites this paper.

IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-05T21:08:17.981943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0be98d1d-5f34-49b5-97ff-6f8f5ccb0bb7 · inbound

Backdoor Attacks on Prompt-Driven Video Segmentation Foundation Models cites this paper.

Backdoor Attacks on Prompt-Driven Video Segmentation Foundation Models Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

Reference 66

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T19:11:11.718943Z

Source-reported events for the cited work

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

Observation 49772814-d447-4fed-a4a4-27e2ce8f46ab · inbound

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

SlowBA: An efficiency backdoor attack towards VLM-based GUI agents Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

Reference 69

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

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30b0c0de-db8f-47a1-ae51-c1c7b5cdaca8 · inbound

Phantasia: Context-Adaptive Backdoors in Vision Language Models cites this paper.

Phantasia: Context-Adaptive Backdoors in Vision Language Models Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:11:01.191590Z

Source-reported events for the cited work

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

Observation e024a2da-535e-4c3d-be5b-9a9eaf423334 · inbound

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety cites this paper.

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

Reference 195

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T12:46:06.925920Z

Source-reported events for the cited work

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

Observation 18780b23-03e8-4a2b-85e3-e035ab665efb · inbound

EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy cites this paper.

EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:48:57.414580Z

Source-reported events for the cited work

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