corpus.blog
41,554 blogs · 4,969,865 posts Claim your blog
Record · corpus.blog/posts/01a0875f-b7bb-7379-ba9c-ab82a9f9f676

Multimodal prompt injection: attacks in images, audio, and video

christian-schneider.net · published 11 March 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at christian-schneider.net Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
22
Words captured
3,748

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://www.nature.com/articles/s41467-024-55631-x
nature.com
https://genai.owasp.org/llmrisk/llm01-prompt-injection/
genai.owasp.org
https://arxiv.org/abs/2507.22304
arxiv.org
https://arxiv.org/abs/2311.05608
arxiv.org
https://www.mdpi.com/2079-9292/14/10/1907
mdpi.com
https://www.sciencedirect.com/science/article/abs/pii/S0031320325010520
sciencedirect.com
https://arxiv.org/abs/2410.05346
arxiv.org
https://openaccess.thecvf.com/content/CVPR2025/papers/Xie_Chain_of_Attack_On_the_Robustness_of_Vision-Language_Models_Against_CVPR_2025_paper.pdf
openaccess.thecvf.com
Securing Agentic AI: How Semantic Prompt Injections Bypass AI Guardrails Read at the source ↗
developer.nvidia.com
https://arxiv.org/abs/2510.00181
arxiv.org
https://doi.org/10.1145/3133956.3134052
doi.org
GitHub Copilot: Remote Code Execution via Prompt Injection (CVE-2025-53773) Read at the source ↗
embracethered.com
https://arxiv.org/abs/2407.04482v1
arxiv.org
https://arxiv.org/abs/2512.23881
arxiv.org
https://arxiv.org/abs/2505.14103v1
arxiv.org
https://aclanthology.org/2024.emnlp-main.430.pdf
aclanthology.org
https://www.isca-archive.org/interspeech_2025/alexos25_interspeech.pdf
isca-archive.org
https://arxiv.org/abs/2512.23557
arxiv.org
https://arxiv.org/abs/2503.18813
arxiv.org
https://www.infoq.com/news/2025/04/deepmind-camel-promt-injection/
infoq.com
https://techcrunch.com/2025/12/22/openai-says-ai-browsers-may-always-be-vulnerable-to-prompt-injection-attacks/
techcrunch.com
Fooling AI Agents: Web-Based Indirect Prompt Injection Observed in the Wild Read at the source ↗
unit42.paloaltonetworks.com
Elsewhere on christian-schneider.net (4)