Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding | Paper Citation Record

Observation 88073051-5f25-467e-b525-4dcb62ae96af · outbound

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

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:42.946018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa0ed4e2-7b1c-4fea-aeb4-f8ee063a94d7 · outbound

This paper cites A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:42.952428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48464e29-bed0-41aa-95fd-cd7b66f880e0 · outbound

This paper cites Otter: A Multi-Modal Model with In-Context Instruction Tuning.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Otter: A Multi-Modal Model with In-Context Instruction Tuning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:42.957966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7b280b1-b854-47ed-a925-3f2a87b7ba7f · outbound

This paper cites Visual Instruction Tuning with Polite Flamingo.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Visual Instruction Tuning with Polite Flamingo

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:42.963956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40a1995e-ac82-4e79-8dfe-e86f37f1c55f · outbound

This paper cites Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:42.969519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78a336fa-2d84-49a0-a459-d99fc6e57dbf · outbound

This paper cites Adversarial Attacks in Multimodal Systems: A Practitioner's Survey.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Adversarial Attacks in Multimodal Systems: A Practitioner's Survey

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-06T11:54:43.863037Z

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 8cb51be9-59d3-4538-8bc7-c44f705f60b4 · outbound

This paper cites Prompt Injection attack against LLM-integrated Applications.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Prompt Injection attack against LLM-integrated Applications

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:42.985770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0fb3c20-d6dd-48da-a02f-d3d2e7691f1a · outbound

This paper cites An Early Categorization of Prompt Injection Attacks on Large Language Models.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding An Early Categorization of Prompt Injection Attacks on Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:42.991098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b75b21fd-8389-42fd-906e-28d015261e01 · outbound

This paper cites Dissecting Adversarial Robustness of Multimodal LM Agents.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Dissecting Adversarial Robustness of Multimodal LM Agents

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:42.996988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06bad409-a55c-41cf-b570-772d941b7300 · outbound

This paper cites Web Artifact Attacks Disrupt Vision Language Models.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Web Artifact Attacks Disrupt Vision Language Models

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-06T11:54:43.788498Z

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 89d03e20-79d7-4133-9a52-f2c60d123ec4 · outbound

This paper cites an unresolved cited work.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:54:44.388374Z

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 61cd7451-7d28-4ebf-be93-ee74146bf449 · outbound

This paper cites ”Prompt injection attacks on vision-language models for surgical decision support” medRxiv (2025).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Prompt injection attacks on vision-language models for surgical decision support” medRxiv (2025)

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.372916Z

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 5faea211-9aca-45a4-93cb-9df307c7998b · outbound

This paper cites VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.022503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d133490-41c1-4cd4-92fe-41aa5c4f1c24 · outbound

This paper cites Adversarial Attacks to Multi-Modal Models.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Adversarial Attacks to Multi-Modal Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.027701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1d2853d-4266-4254-a13c-3334035f4fd6 · outbound

This paper cites ”Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs” arXiv preprint arXiv:2410.03768 (2024).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs” arXiv preprint arXiv:2410.03768 (2024)

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.032650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9f03677-1337-4149-808e-22d3de271ec2 · outbound

This paper cites Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.037974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05790bc7-0bd0-47fe-8d63-c173ba9f2dfd · outbound

This paper cites an unresolved cited work.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:54:44.357472Z

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 c423b82f-43dc-4201-8622-adecfda238d7 · outbound

This paper cites ”A deep learning-driven multi-layered steganographic approach for enhanced data security” Scientific Reports (2025).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”A deep learning-driven multi-layered steganographic approach for enhanced data security” Scientific Reports (2025)

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.342391Z

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 b815fd14-b3d3-4ef2-9909-d1917dada538 · outbound

This paper cites ”Cross: Diffusion model makes controllable, robust and se- cure image steganography” Advances in Neural Information Processing Systems (2024).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Cross: Diffusion model makes controllable, robust and se- cure image steganography” Advances in Neural Information Processing Systems (2024)

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.326963Z

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 93863ce8-500c-4d98-9452-654f0d4f6186 · outbound

This paper cites Defeating Prompt Injections by Design.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Defeating Prompt Injections by Design

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.059837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1aa5956-f218-42c4-899f-c26180dafe67 · outbound

This paper cites Learning Transferable Visual Models From Natural Language Supervision.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Learning Transferable Visual Models From Natural Language Supervision

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.065058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efaffa51-15c5-4033-92bc-22b8c0885f50 · outbound

This paper cites Visual Instruction Tuning.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Visual Instruction Tuning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.070875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7b1fc11-e328-4108-92ea-7790a1eec5a8 · outbound

This paper cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.076150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3863703-51e5-41df-9d6c-1d1c333341cb · outbound

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

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.081752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6660585-77e4-41be-8d93-278b03665702 · outbound

This paper cites ”LLM01:2025 Prompt Injection” Retrieved from https://genai.owasp.org/llmrisk/llm01-prompt-injection/ (2025).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”LLM01:2025 Prompt Injection” Retrieved from https://genai.owasp.org/llmrisk/llm01-prompt-injection/ (2025)

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.312094Z

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 e18f1516-8b0b-41d8-9fd9-1a0c20477330 · outbound

This paper cites ”Text-Based Prompt Injection Attack Using Mathematical Functions in Modern Large Language Models” Electronics, 13(24), 5008 (2024).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Text-Based Prompt Injection Attack Using Mathematical Functions in Modern Large Language Models” Electronics, 13(24), 5008 (2024)

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.297019Z

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 ff24a6f7-1b78-4c9c-961c-100377eb7315 · outbound

This paper cites Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.097851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66bdaf77-91db-4f8e-94f4-bc4d9b3abb2d · outbound

This paper cites Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injection.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injection

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.102709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44c7eb62-663a-43ba-9778-8aaa00fd2949 · outbound

This paper cites ”Detecting LSB Steganography in Color and Gray- Scale Images” IEEE Multimedia (2001).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Detecting LSB Steganography in Color and Gray- Scale Images” IEEE Multimedia (2001)

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.280152Z

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 bbc8d8c9-e93d-47d2-b873-4ed7995c42f5 · outbound

This paper cites ”Image steganography techniques for resisting statistical steganalysis attacks: A systematic literature review” PLOS One, 19(9), e0308807 (2024).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Image steganography techniques for resisting statistical steganalysis attacks: A systematic literature review” PLOS One, 19(9), e0308807 (2024)

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.263879Z

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 270baea9-cb96-42de-8eaf-2e8f682e8dfd · outbound

This paper cites ”Super-resolution deep neural network (SRDNN) based multi-image steganography for highly secured lossless image transmission” Scientific Reports, 14, 6104 (2024).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Super-resolution deep neural network (SRDNN) based multi-image steganography for highly secured lossless image transmission” Scientific Reports, 14, 6104 (2024)

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.248568Z

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 a8910583-ccd1-4868-9007-42ab78c296ab · outbound

This paper cites ”Comprehensive survey on image steganalysis using deep learning” Neural Computing and Applications (2024).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Comprehensive survey on image steganalysis using deep learning” Neural Computing and Applications (2024)

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.232576Z

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 30efcbe0-0321-4a05-b971-2b5d5ebb4d57 · outbound

This paper cites ”Enhancing Steganography Detection with AI: Fine-Tuning a Deep Residual Network for Spread Spectrum Image Steganography” PMC (2024).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Enhancing Steganography Detection with AI: Fine-Tuning a Deep Residual Network for Spread Spectrum Image Steganography” PMC (2024)

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.215604Z

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 0fd1c21d-9986-4e1d-bc6e-77c6063d7da6 · outbound

This paper cites ”Digital image steganalysis network strengthening framework based on evolutionary algorithm” Scientific Reports (2025).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Digital image steganalysis network strengthening framework based on evolutionary algorithm” Scientific Reports (2025)

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.199128Z

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 7914237f-2d7f-42e4-9bd3-efdbfbac8e98 · outbound

This paper cites ”An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale” ICLR (2021).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale” ICLR (2021)

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.182922Z

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 76282668-2978-4050-a710-ff401cb55df0 · outbound

This paper cites Improved Baselines with Visual Instruction Tuning.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Improved Baselines with Visual Instruction Tuning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.143299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c756846d-6e30-4681-94be-ad3a3ba03b22 · outbound

This paper cites an unresolved cited work.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:54:44.167283Z

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 546f64ed-bc4f-46f2-b00c-a17c7af023ba · outbound

This paper cites BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.153675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efa2767d-71fe-4e26-b13c-928d44c44778 · outbound

This paper cites ”PSNR vs SSIM: imperceptibility quality assessment for image steganography” Multimedia Tools and Applications, 80, 8423- 8444 (2021).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”PSNR vs SSIM: imperceptibility quality assessment for image steganography” Multimedia Tools and Applications, 80, 8423- 8444 (2021)

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.151445Z

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 fc260326-9023-4e34-8a65-37a3c558bcd3 · outbound

This paper cites ”Hiding data in images by simple LSB substitution” Pattern Recognition (2004).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Hiding data in images by simple LSB substitution” Pattern Recognition (2004)

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.135985Z

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 099316a3-ff37-4b6f-9ce8-96cef00cb4f2 · outbound

This paper cites ”Attacks on steganographic systems” Information Hiding Workshop (1999).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Attacks on steganographic systems” Information Hiding Workshop (1999)

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.120681Z

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 f684a847-a30f-4025-aba8-cd3f807c893b · outbound

This paper cites ”Secure spread spectrum watermarking for multimedia” IEEE Transactions on Image Processing (1997).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Secure spread spectrum watermarking for multimedia” IEEE Transactions on Image Processing (1997)

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.105413Z

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 d6588eb5-fb3a-4692-bf8b-e625baa6c2f9 · outbound

This paper cites ”An Analysis of LSB & DCT based Steganography”.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”An Analysis of LSB & DCT based Steganography”

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.088020Z

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 2452c1e6-1fce-408c-9e48-a2124e8eee8d · outbound

This paper cites CNN-Assisted Steganography -- Integrating Machine Learning with Established Steganographic Techniques.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding CNN-Assisted Steganography -- Integrating Machine Learning with Established Steganographic Techniques

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-08-06T11:54:43.478459Z

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 8183c266-9177-4a62-8d78-df6ac83b5573 · outbound

This paper cites ”Hiding images in plain sight: Deep steganography” Advances in Neural Information Processing Systems (2017).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Hiding images in plain sight: Deep steganography” Advances in Neural Information Processing Systems (2017)

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.072404Z

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 3dd6cc42-4794-4c63-8194-cced2f12c9f0 · outbound

This paper cites Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.197642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a9f7517-49f3-4676-9a0c-5e70355a2cdf · outbound

This paper cites ”Peak signal-to-noise ratio” Wikipedia.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Peak signal-to-noise ratio” Wikipedia

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.049748Z

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 8a574751-d214-443a-ac91-1db79e52a918 · outbound

This paper cites ”Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game” arXiv preprint (2023).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game” arXiv preprint (2023)

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.032866Z

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 1f633e2a-357d-4cbb-98ad-f6f0f3e823a9 · outbound

This paper cites ”A survey on large language model (llm) security and privacy: The good, the bad, and the ugly” High-Confidence Computing, 4, 100211 (2024).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”A survey on large language model (llm) security and privacy: The good, the bad, and the ugly” High-Confidence Computing, 4, 100211 (2024)

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:44.015017Z

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 b5e09b79-2780-4426-90c7-d3cdfe4dc690 · outbound

This paper cites ”Exploring steganography: Seeing the unseen” Computer (2008).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Exploring steganography: Seeing the unseen” Computer (2008)

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:43.998757Z

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 9d955cd4-0d35-433e-81a8-52d7524f3468 · outbound

This paper cites ”Steganalysis by subtractive pixel adjacency matrix” IEEE Transactions on Information Forensics and Security.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Steganalysis by subtractive pixel adjacency matrix” IEEE Transactions on Information Forensics and Security

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:43.982581Z

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 2154cf33-6248-4ac0-b8d1-10c78b5966e0 · outbound

This paper cites Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.224102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1851ec6-ff7a-4618-983d-1670f5d9ff74 · outbound

This paper cites ”Visual Adversarial Examples Jailbreak Aligned Large Language Models” AAAI Conference on Artificial Intelligence (2023).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Visual Adversarial Examples Jailbreak Aligned Large Language Models” AAAI Conference on Artificial Intelligence (2023)

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:54:43.965905Z

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 44628e35-95c1-46cb-a172-88e77b633620 · outbound

This paper cites Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.232843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab267661-edec-4b18-867d-7e5e639b23d1 · outbound

This paper cites On the Robustness of Large Multimodal Models Against Image Adversarial Attacks.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding On the Robustness of Large Multimodal Models Against Image Adversarial Attacks

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.237746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e0b78cb-4f63-44f2-bcbf-5a7b8fd736bb · outbound

This paper cites Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey.

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T11:54:43.242527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a3eaf97-d3b9-4e58-8a25-23c033edbcfa · outbound

This paper cites ”Image-based Multimodal Models as Intruders: Trans- ferable Multimodal Attacks on Video-based MLLMs” arXiv preprint arXiv:2501.01042 (2025).

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding ”Image-based Multimodal Models as Intruders: Trans- ferable Multimodal Attacks on Video-based MLLMs” arXiv preprint arXiv:2501.01042 (2025)

Reference 57

Resolution: verified exact; raw_fallback, observed 2026-08-06T11:54:43.360766Z

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