arXiv (All)
open access
The Uncontrolled Variable: Vision-Language Model Refusal Responds to Image Presence in Ways Risk Cannot Explain
Vision-Language Model (VLM) safety is expected to depend on what a request asks for. We show that safety-aligned VLMs also key refusal on a property of a request's form: whether an image is attached, holding everything the request asks fixed. Attaching a blank canvas - unreadable, unrelated to the r
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
- Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack#1117452
- To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model#187257
- It Takes Little to Rewrite Perception: Targeted Semantic Substitution in Vision-Language Models at $ε\leq 4/255$#1142899
- Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms#141781
- Invisible in Space, Visible in Time: Motion Vision CAPTCHA against GUI Agents#1063672
Record · ID 1062075
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