Text Prompt Injection of Vision Language Models

Ruizhe Zhu
10/10/2025
cs.CLcs.CV

No confident code implementation found for this paper. 5 possible matches can be shown below.

Abstract

The widespread application of large vision language models has significantly raised safety concerns. In this project, we investigate text prompt injection, a simple yet effective method to mislead these models. We developed an algorithm for this type of attack and demonstrated its effectiveness and efficiency through experiments. Compared to other attack methods, our approach is particularly effective for large models without high demand for computational resources.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 5 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Physical Prompt Injection Attacks on Large Vision-Language Models

88% match1 repo62026

Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors

88% match2024

Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injection

87% match2024

Adversarial Prompt Injection Attack on Multimodal Large Language Models

86% match2026

Enhancing Cross-Prompt Transferability in Vision-Language Models through Contextual Injection of Target Tokens

86% match1 repo32024

Prompt Injection Attacks on Large Language Models in Oncology

85% match2024

Cite this paper

@article{zhu2025text,
  title  = {Text Prompt Injection of Vision Language Models},
  author = {Ruizhe Zhu},
  year   = {2025},
  eprint = {2510.09849},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.09849v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.09849.svg)](https://codeofpaper.com/paper/2510.09849)

Discussion