One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models | Paper Citation Record

Observation 2f8da359-dda7-4ee8-beac-ffae3b37f341 · outbound

This paper cites Image Hijacks: Adversarial Images can Control Generative Models at Runtime.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Image Hijacks: Adversarial Images can Control Generative Models at Runtime

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:52.561526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3db6e712-840e-4f4f-9369-dfb8f3bb4cc8 · outbound

This paper cites Context-aware transfer attacks for ob- ject detection.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Context-aware transfer attacks for ob- ject detection

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:04.582831Z

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 cb3ca466-26d7-4f9c-800f-e24313583aaa · outbound

This paper cites Attentional feature erase: Towards task-wise transferable ad- versarial attack on cloud vision apis.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Attentional feature erase: Towards task-wise transferable ad- versarial attack on cloud vision apis

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:04.442856Z

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 c3a0dd3f-ed1f-4e0c-995f-67ef7435c8ac · outbound

This paper cites Unihcp: A unified model for human-centric perceptions.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Unihcp: A unified model for human-centric perceptions

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:04.319792Z

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 30441227-0aae-4551-b6c4-15b183795279 · outbound

This paper cites On the robustness of large multimodal mod- els against image adversarial attacks.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models On the robustness of large multimodal mod- els against image adversarial attacks

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:03.750825Z

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 37777eec-ccad-48b1-bd52-14a4fd214294 · outbound

This paper cites How Robust is Google's Bard to Adversarial Image Attacks?.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models How Robust is Google's Bard to Adversarial Image Attacks?

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:52.995040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff96f19c-ec7e-4948-a64a-82344e57d4e7 · outbound

This paper cites Enhancing cross-task transferability of adversarial examples via spatial and channel attention.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Enhancing cross-task transferability of adversarial examples via spatial and channel attention

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:03.304111Z

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 091de147-a505-4436-a2d7-11f0cfe5edfa · outbound

This paper cites Similarity distribution based member- ship inference attack on person re-identification.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Similarity distribution based member- ship inference attack on person re-identification

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:03.132963Z

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 fefae3bc-8a0e-4453-9ca0-e62891356bb3 · outbound

This paper cites StyleShot: A Snapshot on Any Style.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models StyleShot: A Snapshot on Any Style

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:53.311135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3188f16-bc79-4f29-aabe-9843ffcda28f · outbound

This paper cites FaceShot: Bring Any Character into Life.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models FaceShot: Bring Any Character into Life

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:53.394152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b983c199-f9c3-4990-a2f9-4c7706473495 · outbound

This paper cites OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:53.470204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd5eb1e8-d046-4977-91f4-fd5532a5a8fe · outbound

This paper cites Instruct-reid: A multi-purpose person re-identification task with instructions.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Instruct-reid: A multi-purpose person re-identification task with instructions

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:02.955618Z

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 baaba23d-1ee4-4601-b239-46fea2c9df48 · outbound

This paper cites As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:53.632624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb5915ce-7eb7-47b9-893a-10c4cb984cb7 · outbound

This paper cites VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:53.704274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfcfadd7-574e-45d0-a21b-af7f46ff028e · outbound

This paper cites You only learn one query: learning unified human query for single-stage multi-person multi-task human-centric perception.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models You only learn one query: learning unified human query for single-stage multi-person multi-task human-centric perception

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:02.740204Z

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 e1c1d7c0-ed12-495c-8cb9-19780b58d9e0 · outbound

This paper cites Uni-perceiver v2: A generalist model for large-scale vision and vision-language tasks.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Uni-perceiver v2: A generalist model for large-scale vision and vision-language tasks

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:02.509060Z

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 12d9eb59-564e-43c8-88cb-21505bd9f301 · outbound

This paper cites Lawrence Zitnick, and Piotr Doll ´ar.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Lawrence Zitnick, and Piotr Doll ´ar

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:53.988758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed8edf02-b147-4fc6-ac77-8a5a5de05570 · outbound

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

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:54.067388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc66f181-7a58-465f-bf25-f3f01a85b8d3 · outbound

This paper cites Set-level guidance at- tack: Boosting adversarial transferability of vision-language pre-training models.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Set-level guidance at- tack: Boosting adversarial transferability of vision-language pre-training models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:54.203313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdffc7f7-40e6-4887-8555-98cfcf71faa1 · outbound

This paper cites Unified-io: A unified model for vision, language, and multi-modal tasks.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Unified-io: A unified model for vision, language, and multi-modal tasks

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:02.280919Z

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 36eb2baa-6703-4f23-9aaf-38290c0bc1c8 · outbound

This paper cites Unified-io 2: Scaling autoregressive multimodal models with vision language audio and action.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Unified-io 2: Scaling autoregressive multimodal models with vision language audio and action

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:02.078187Z

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 cb1146a3-bd8d-4fcf-ac0c-9d57208023e3 · outbound

This paper cites Time-aware and task-transferable adversarial attack for perception of autonomous vehicles.Pattern Recog- nition Letters, 178:145–152, 2024.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Time-aware and task-transferable adversarial attack for perception of autonomous vehicles.Pattern Recog- nition Letters, 178:145–152, 2024

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:01.886473Z

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 37e12be3-0ec8-48d6-967f-f8e319d40979 · outbound

This paper cites An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:54.618030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf0976d6-02f5-44b1-b7f0-12e3af5c7c5f · outbound

This paper cites CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:40:58.228144Z

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 ba9e5470-1587-4edc-8dd0-e37d450d6e72 · outbound

This paper cites Boosting Cross-task Transferability of Adversarial Patches with Visual Relations.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Boosting Cross-task Transferability of Adversarial Patches with Visual Relations

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:40:58.008920Z

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 7cf09c22-42a0-4e37-a66f-1df952a4045c · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:54.870153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e52c3ca0-5ef8-4b6e-9c1a-7882d9d7e190 · outbound

This paper cites Pick-object-attack: Type-specific adver- sarial attack for object detection.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Pick-object-attack: Type-specific adver- sarial attack for object detection

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:01.680509Z

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 6210a3bf-b9ab-474a-afd8-9f081f7babf3 · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models High-resolution image synthesis with latent diffusion models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:55.065487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 690ee877-f126-4ae8-a2e4-30c805c78141 · outbound

This paper cites On the adversarial robustness of multi-modal foundation models.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models On the adversarial robustness of multi-modal foundation models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:01.372958Z

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 3d7d6066-fd24-45ac-8c83-4a4e5f8b3755 · outbound

This paper cites Unival: Unified model for image, video, au- dio and language tasks.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Unival: Unified model for image, video, au- dio and language tasks

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:01.242798Z

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 ed55307c-ca35-43ce-8faf-54be1420f9b4 · outbound

This paper cites How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:55.324196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66b395ff-f43f-4caf-9df5-2b2d593ffe5a · outbound

This paper cites Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:40:57.847447Z

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 975aab70-7a35-4614-acaa-9826b4a493fb · outbound

This paper cites Trans- ferable multimodal attack on vision-language pre-training models.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Trans- ferable multimodal attack on vision-language pre-training models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:01.051120Z

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 62d80cd7-bb56-45f7-91ea-ec1acf13d2b4 · outbound

This paper cites Psat-gan: Efficient adversarial attacks against holistic scene understanding.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Psat-gan: Efficient adversarial attacks against holistic scene understanding

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:00.765996Z

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 333a1558-1b7f-4999-a79b-0d5bc920c63d · outbound

This paper cites Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:00.517543Z

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 6d531dda-82d0-47a8-8c3f-e904bbc6a45a · outbound

This paper cites Florence-2: Advancing a unified representation for a variety of vision tasks.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Florence-2: Advancing a unified representation for a variety of vision tasks

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:00.237652Z

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 f2cb06d3-c0d4-4321-a064-1f723a32706b · outbound

This paper cites Highly transferable diffusion- based unrestricted adversarial attack on pre-trained vision- language models.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Highly transferable diffusion- based unrestricted adversarial attack on pre-trained vision- language models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:41:00.055108Z

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 84623cfd-f757-4cda-96d5-36829323f5cc · outbound

This paper cites Cross-task attack: A self-supervision generative framework based on attention shift.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Cross-task attack: A self-supervision generative framework based on attention shift

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:40:59.957900Z

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 5429ed14-2dde-4b16-a62b-7f8d50e38193 · outbound

This paper cites X 2-vlm: All-in-one pre- trained model for vision-language tasks.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models X 2-vlm: All-in-one pre- trained model for vision-language tasks

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:40:59.832721Z

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 8a8dffec-ce67-4e58-a44e-82eece6136dc · outbound

This paper cites AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:56.361825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b780a49f-a376-415a-8917-7617f7da2731 · outbound

This paper cites Boosting cross-task ad- versarial attack with random blur.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Boosting cross-task ad- versarial attack with random blur

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:40:59.685449Z

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 725e31c0-b536-4742-97ad-0493024588b4 · outbound

This paper cites MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:56.640539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae77c430-515f-4bf9-91e3-5f0fe51a8cea · outbound

This paper cites On evalu- ating adversarial robustness of large vision-language mod- els.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models On evalu- ating adversarial robustness of large vision-language mod- els

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:40:59.526994Z

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 753e6600-fc65-4ec5-9215-345b6ed9fb67 · outbound

This paper cites Adversarial Attacks on Hidden Tasks in Multi-Task Learning.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Adversarial Attacks on Hidden Tasks in Multi-Task Learning

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:56.852843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 882c643c-6fa5-4204-aad1-d9350f8dea7a · outbound

This paper cites [SOURCE_CATEGORY].

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models [SOURCE_CATEGORY]

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:40:59.397624Z

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 95d8fee4-d11c-46c8-8f4a-d1fd636aa1fe · outbound

This paper cites [SOURCE_CATEGORY].

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models [SOURCE_CATEGORY]

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:40:59.265668Z

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 d581e584-df30-462d-9b0a-871592095111 · outbound

This paper cites The procedure begins by initializing the adversar- ial example and locating the token indices corresponding to the source object region.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models The procedure begins by initializing the adversar- ial example and locating the token indices corresponding to the source object region

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:40:59.135566Z

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 a5b59517-f6a5-401b-933d-d79d79e7f70b · outbound

This paper cites Implementation Details of Compared Methods We provide detailed implementation information for all compared methods to ensure reproducibility and fair com- parison.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Implementation Details of Compared Methods We provide detailed implementation information for all compared methods to ensure reproducibility and fair com- parison

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:40:58.931303Z

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 cbac4c34-80d3-46fc-b9fd-8365fcdcd007 · outbound

This paper cites an unresolved cited work.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:40:58.728434Z

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 139d7a7e-d3f2-43d7-b244-930bae5cba33 · outbound

This paper cites Comparison with object detection attack baselines on Florence-2.

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models Comparison with object detection attack baselines on Florence-2

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:40:58.530056Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers