Paper Citation Record · LEDGER

Adversarial-Guided Diffusion for Multimodal LLM Attacks

As of 7 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 1 inbound Pith citation observation for arXiv:2507.23202.

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

pith.paper-citation-record.v1
2507.23202 v1

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T11:02:15.122716Z

measured 48 of 48 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-17T04:15:38.632039Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-17T04:19:00.663878Z

Reference resolution

47 of 47 outbound references displayed

verified exact0
verified fuzzy37
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 355b679a-62d3-4fc7-9471-be2b086b490b · outbound

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

Adversarial-Guided Diffusion for Multimodal LLM Attacks Image Hijacks: Adversarial Images can Control Generative Models at Runtime

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T11:02:14.914452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c62a5ea3-2c0e-4f90-b56d-9a999fc89421 · outbound

This paper cites One transformer fits all distributions in multi-modal diffusion at scale.

Adversarial-Guided Diffusion for Multimodal LLM Attacks One transformer fits all distributions in multi-modal diffusion at scale

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.827406Z

Source-reported events for the cited work

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

Observation ed2edd90-7dc1-4ab1-9044-a9fe90407b89 · outbound

This paper cites A young boy is playing with a baseball bat A blue bird sitting on a tree branch.

Adversarial-Guided Diffusion for Multimodal LLM Attacks A young boy is playing with a baseball bat A blue bird sitting on a tree branch

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.812072Z

Source-reported events for the cited work

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

Observation 8cfd7638-7b51-4029-b89f-d3b4623b3371 · outbound

This paper cites Content-based unrestricted ad- versarial attack.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Content-based unrestricted ad- versarial attack

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.796284Z

Source-reported events for the cited work

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

Observation 43c1d343-721e-4c9b-9976-bf266da9df9c · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T11:02:14.933642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7da7aae7-cc41-4aad-a373-23eae82ad1ae · outbound

This paper cites On the robustness of large multimodal models against image adversarial attacks.

Adversarial-Guided Diffusion for Multimodal LLM Attacks On the robustness of large multimodal models against image adversarial attacks

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.771932Z

Source-reported events for the cited work

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

Observation ea777a4e-a16d-430e-913a-37b9db5a75a3 · outbound

This paper cites Advdiff: Gener- ating unrestricted adversarial examples using diffusion mod- els.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Advdiff: Gener- ating unrestricted adversarial examples using diffusion mod- els

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.756979Z

Source-reported events for the cited work

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

Observation a9e5bb1a-6779-4920-9501-d2b71f216fbf · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Imagenet: A large-scale hierarchical image database

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.742560Z

Source-reported events for the cited work

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

Observation 1eff578d-0d10-405b-8c4a-a89b2f974b38 · outbound

This paper cites Diffusion models beat gans on image synthesis.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Diffusion models beat gans on image synthesis

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.728424Z

Source-reported events for the cited work

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

Observation d39f371d-39c2-4fbd-9777-b201dad081b0 · outbound

This paper cites Boosting adversarial attacks with momentum.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Boosting adversarial attacks with momentum

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.712765Z

Source-reported events for the cited work

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

Observation b9826d94-4775-43a8-a039-7694b7706696 · outbound

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

Adversarial-Guided Diffusion for Multimodal LLM Attacks How Robust is Google's Bard to Adversarial Image Attacks?

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T11:02:14.960784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e114afd-e268-4d72-9ac3-ab5fad0b6b42 · outbound

This paper cites Boosting transferability in vision-language attacks via diversification along the intersection region of adversarial trajectory.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Boosting transferability in vision-language attacks via diversification along the intersection region of adversarial trajectory

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.696870Z

Source-reported events for the cited work

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

Observation 9d98356a-7fe0-4169-8c65-0819517a3348 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Explaining and Harnessing Adversarial Examples

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T11:02:14.969893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40094e0f-ff89-48d0-9b8b-b0e40e089cca · outbound

This paper cites Countering adversarial images using input transformations.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Countering adversarial images using input transformations

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.682257Z

Source-reported events for the cited work

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

Observation 8f08cde7-e584-4a2b-92af-41595ce571b0 · outbound

This paper cites Efficient generation of targeted and transferable adversarial examples for vision-language models via diffusion models.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Efficient generation of targeted and transferable adversarial examples for vision-language models via diffusion models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.668808Z

Source-reported events for the cited work

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

Observation ce8e715b-987c-4036-b6a3-0bdd58c39024 · outbound

This paper cites CLIPScore: A Reference-free Evaluation Metric for Image Captioning.

Adversarial-Guided Diffusion for Multimodal LLM Attacks CLIPScore: A Reference-free Evaluation Metric for Image Captioning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T11:02:14.982876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbeb103f-dd5f-447a-9cba-fe9f26260fd9 · outbound

This paper cites Denoising dif- fusion probabilistic models.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Denoising dif- fusion probabilistic models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.654654Z

Source-reported events for the cited work

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

Observation a0fd4630-ad7e-431b-b88f-6d86aa957d1e · outbound

This paper cites Image quality metrics: PSNR vs.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Image quality metrics: PSNR vs

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.640388Z

Source-reported events for the cited work

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

Observation 214fd654-b65c-4003-abec-a7aedbf41fd1 · outbound

This paper cites An edit friendly DDPM noise space: Inversion and manipulations.

Adversarial-Guided Diffusion for Multimodal LLM Attacks An edit friendly DDPM noise space: Inversion and manipulations

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.626446Z

Source-reported events for the cited work

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

Observation 408d3b56-bf24-4c99-aaff-e5bc562280d8 · outbound

This paper cites Adver- sarial examples in the physical world.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Adver- sarial examples in the physical world

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.612897Z

Source-reported events for the cited work

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

Observation 31427e88-15fd-4926-98db-31adef6eef64 · outbound

This paper cites BLIP- 2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

Adversarial-Guided Diffusion for Multimodal LLM Attacks BLIP- 2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.598359Z

Source-reported events for the cited work

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

Observation f1c3f962-7457-467b-b8c6-4ffac2d56bda · outbound

This paper cites Alleviating exposure bias in diffusion mod- els through sampling with shifted time steps.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Alleviating exposure bias in diffusion mod- els through sampling with shifted time steps

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.584000Z

Source-reported events for the cited work

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

Observation ef11b07c-9782-4cb0-8a28-b5528660f3fc · outbound

This paper cites Microsoft coco: Common objects in context.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Microsoft coco: Common objects in context

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.569838Z

Source-reported events for the cited work

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

Observation cbbef974-6413-46e9-ba9d-e167a530eea9 · outbound

This paper cites Visual instruction tuning.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Visual instruction tuning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.556325Z

Source-reported events for the cited work

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

Observation 5c7dc2c4-804f-4b44-9a9b-965a6527b0c3 · outbound

This paper cites An image is worth 1000 lies: Transferability of adversarial images across prompts on vision-language models.

Adversarial-Guided Diffusion for Multimodal LLM Attacks An image is worth 1000 lies: Transferability of adversarial images across prompts on vision-language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.542148Z

Source-reported events for the cited work

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

Observation f4a17c9f-5bb1-4c49-be9b-dce19e67ce83 · outbound

This paper cites Towards deep learning models resistant to adversarial attacks.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Towards deep learning models resistant to adversarial attacks

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.527782Z

Source-reported events for the cited work

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

Observation 50ea609c-f535-4734-a01c-524e94c74e70 · outbound

This paper cites Diffusion models for adver- sarial purification.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Diffusion models for adver- sarial purification

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.513080Z

Source-reported events for the cited work

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

Observation a511cb04-afc6-4ed2-a4ea-1e941ae13228 · outbound

This paper cites Elucidating the exposure bias in diffusion models.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Elucidating the exposure bias in diffusion models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.497478Z

Source-reported events for the cited work

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

Observation 1bb54fcc-389b-4a0d-9855-660aba02800d · outbound

This paper cites Diffusion-based adversarial purification from the perspective of the frequency domain.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Diffusion-based adversarial purification from the perspective of the frequency domain

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.482788Z

Source-reported events for the cited work

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

Observation 727d9050-e03a-4864-b857-6dd747222847 · outbound

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

Adversarial-Guided Diffusion for Multimodal LLM Attacks Learning transferable visual models from natural language supervision

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.467217Z

Source-reported events for the cited work

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

Observation 31e551c4-e73d-466f-b09d-3b1e7e34cac1 · outbound

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

Adversarial-Guided Diffusion for Multimodal LLM Attacks High-resolution image synthesis with latent diffusion models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.450877Z

Source-reported events for the cited work

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

Observation 3bd7ad07-2919-4afa-8849-02fb81a9afe1 · outbound

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

Adversarial-Guided Diffusion for Multimodal LLM Attacks On the adversarial robustness of multi-modal foundation models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.435503Z

Source-reported events for the cited work

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

Observation 1d2d9dd0-1b31-4405-b770-07d3b477b859 · outbound

This paper cites Colorfool: Semantic adversarial colorization.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Colorfool: Semantic adversarial colorization

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.420741Z

Source-reported events for the cited work

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

Observation bc3e488a-5e85-4808-841d-5d189f4a3b79 · outbound

This paper cites Jail- break in pieces: Compositional adversarial attacks on multi- modal language models.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Jail- break in pieces: Compositional adversarial attacks on multi- modal language models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.405081Z

Source-reported events for the cited work

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

Observation bae917c7-7b58-45f1-b9d2-f7f48a7068ad · outbound

This paper cites Online adver- sarial purification based on self-supervised learning.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Online adver- sarial purification based on self-supervised learning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.390395Z

Source-reported events for the cited work

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

Observation c00f31dc-710f-408c-a5d4-0bc5bacad6cd · outbound

This paper cites Denoising diffusion implicit models.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Denoising diffusion implicit models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T11:02:15.072519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c2e1d6e-1a51-4457-be0e-0384a7c229e4 · outbound

This paper cites Mimicd- iffusion: Purifying adversarial perturbation via mimicking clean diffusion model.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Mimicd- iffusion: Purifying adversarial perturbation via mimicking clean diffusion model

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.364656Z

Source-reported events for the cited work

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

Observation f65b2e99-3099-4cde-b75c-80ce463fffd3 · outbound

This paper cites Score-based generative modeling through stochastic differential equations.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Score-based generative modeling through stochastic differential equations

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.348642Z

Source-reported events for the cited work

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

Observation c98a7ae5-613d-45d5-8ff1-b16b0535429f · outbound

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

Adversarial-Guided Diffusion for Multimodal LLM Attacks Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T11:02:15.086370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14958a04-56bc-472c-8388-e05fc11b603e · outbound

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

Adversarial-Guided Diffusion for Multimodal LLM Attacks InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T11:02:15.091090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33d31752-896c-474b-95cd-dfce17e8229b · outbound

This paper cites Image quality assessment: from error visibility to structural similarity.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Image quality assessment: from error visibility to structural similarity

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.333637Z

Source-reported events for the cited work

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

Observation bc8304a8-8afa-4303-aa18-e2cdd28a4522 · outbound

This paper cites Mitigating adversarial effects through random- ization.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Mitigating adversarial effects through random- ization

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.319280Z

Source-reported events for the cited work

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

Observation 5d5a302d-2b00-4e73-a96b-f4b036e5c619 · outbound

This paper cites Chain of attack: On the robustness of vision-language models against transfer-based adversarial attacks.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Chain of attack: On the robustness of vision-language models against transfer-based adversarial attacks

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.304421Z

Source-reported events for the cited work

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

Observation 82f6430f-0593-4b79-bf21-46030dd5cbf3 · outbound

This paper cites Natural color fool: Towards boosting black-box unrestricted attacks.

Adversarial-Guided Diffusion for Multimodal LLM Attacks Natural color fool: Towards boosting black-box unrestricted attacks

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.289407Z

Source-reported events for the cited work

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

Observation d4166f59-ccd9-45ee-b60e-297ded55cfd8 · outbound

This paper cites The unreasonable effectiveness of deep features as a perceptual metric.

Adversarial-Guided Diffusion for Multimodal LLM Attacks The unreasonable effectiveness of deep features as a perceptual metric

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T11:02:15.113841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fa3b325-939b-4483-95ea-83374ebd26af · outbound

This paper cites On evaluating adversarial robustness of large vision-language models.

Adversarial-Guided Diffusion for Multimodal LLM Attacks On evaluating adversarial robustness of large vision-language models

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:02:15.265738Z

Source-reported events for the cited work

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

Observation dcbb0c16-2e8a-4ace-a906-50d3e31250c2 · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Adversarial-Guided Diffusion for Multimodal LLM Attacks MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T11:02:15.122716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation caf603f1-7592-4b30-b0be-4309dec69664 · inbound

Breaking the Illusion: Consensus-Based Generative Mitigation of Adversarial Illusions in Multi-Modal Embeddings cites this paper.

Breaking the Illusion: Consensus-Based Generative Mitigation of Adversarial Illusions in Multi-Modal Embeddings Adversarial-Guided Diffusion for Multimodal LLM Attacks

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-17T04:19:00.669610Z

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.