arXiv (All)
open access
Before Acting, Change the State: Prospective State Intervention for Web Agents under Deceptive Interfaces
LLM-based Web agents can autonomously complete user tasks, yet deceptive interfaces can steer them toward outcomes that conflict with users' interests. Existing defenses primarily intervene on agent behavior through blocking, guidance, or replanning. We identify a distinct failure mode: a task-valid
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
- Before Acting, Change the State: Prospective State Intervention for Web Agents under Deceptive Interfaces#1108627
- Constructing Challenging Browser-Use Tasks by Controlled Environment Interventions#1130656
- Behavioral Fingerprinting and Navigation Prediction in Web Browsing#1012469
- Training Needs Trustworthy Worlds: Verified Synthetic Web Environments for Agent Learning#1129369
- Identifying AI Web Scrapers Using Canary Tokens#926977
Record · ID 1129579
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