arXiv (All)
open access
Beyond the Verdict: Evidence-Aligned Evaluation of Visual Prompt-Injection Guardrails
Verdict-only evaluation does not reveal whether a vision-language model (VLM) used the visual evidence that should support its decision. We study this problem in web-agent guardrails, where a VLM judges whether on-screen text conflicts with a user instruction. We introduce Mind2Web-Injection, a benc
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
- Feed the Panel Dimensions, Not Verdicts: Rubric-Decomposed Fusion of Vision-Language Aesthetic Judges#1063321
- When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation#394461
- Agents in the Large: Perception-Centered Architecture for Persistent Agents#799677
- EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents#973522
- Do Vision-Language Models Understand Visual Persuasiveness? A Diagnosis via Visual Persuasive Factors#998050
Record · ID 972596
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