arXiv CS
open access
Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution
Modern web agents built on large vision-language models process webpages, select relevant UI elements, and translate model outputs into browser actions. Existing visual red-teaming approaches use adversarial visual content to manipulate this process. However, they primarily target model inference an
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
- Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution#1233279
- Automatic Red Teaming for Implicit Vulnerabilities of Text-to-Image Models#973701
- MIRAGE: Stealthy Visual Prompt Injection for Vulnerability Detection in Web Agents#1356090
- APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation#1343288
- CF-JEPA: Improving Robustness of JEPA World Models via Controllability Factorization#1155662
Record · ID 1227273
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