SecureWebArena is a new benchmark suite for holistic security evaluation of LVLM-based web agents using diverse simulated environments, attack taxonomies, and multi-layered failure analysis across reasoning, behavior, and outcomes.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
representative citing papers
PageGuide grounds LLM answers in webpage DOM elements using visual overlays for find, guide, and hide modes, yielding measurable gains in a 94-user study.
CUGA introduces a runtime governance architecture that enforces policies at five checkpoints in generalist agent execution pipelines for predictable and compliant behavior.
citing papers explorer
-
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
SecureWebArena is a new benchmark suite for holistic security evaluation of LVLM-based web agents using diverse simulated environments, attack taxonomies, and multi-layered failure analysis across reasoning, behavior, and outcomes.
-
PageGuide: Browser extension to assist users in navigating a webpage and locating information
PageGuide grounds LLM answers in webpage DOM elements using visual overlays for find, guide, and hide modes, yielding measurable gains in a 94-user study.
-
Governance by Construction for Generalist Agents
CUGA introduces a runtime governance architecture that enforces policies at five checkpoints in generalist agent execution pipelines for predictable and compliant behavior.