arXiv (All)
open access
Render Before Reading: Visual Rendering as a Prompt Injection Defense
Large language models are vulnerable to prompt injection attacks, where third-party adversarial content can hijack the model's behavior. In this paper, we study the role played by the adversarial data's input modality, and identify a systematic asymmetry: multimodal LLMs are more likely to follow ad
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Render Before Reading: Visual Rendering as a Prompt Injection Defense#1122234
- Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks#266128
- UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models#1157238
- Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models#972958
- On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces#349649
Record · ID 1130963
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive