GUIGuard-Bench is a new benchmark with annotated GUI screenshots that measures privacy recognition, planning fidelity under protection, and utility impact for trajectory-based GUI agents.
Can Humans Oversee Agents to Prevent Privacy Leakage? A Study on Privacy Awareness, Preferences, and Trust in Language Model Agents
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Users show limited grasp of GenAI smartphone data practices but heightened privacy concerns across collection, storage, and control, calling for better transparency and user controls.
Oversight strategy in computer-use agents shapes exposure to problematic actions more reliably than correction success, with plan-based approaches reducing occurrences but not uniformly improving interventions.
A 3x3 between-subjects experiment finds that risk-contingent autonomy in LLM agents attenuates personalization's negative effects on privacy concerns and trust via increased perceived control.
citing papers explorer
-
GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents
GUIGuard-Bench is a new benchmark with annotated GUI screenshots that measures privacy recognition, planning fidelity under protection, and utility impact for trajectory-based GUI agents.
-
Understanding User Privacy Perceptions of GenAI Smartphones
Users show limited grasp of GenAI smartphone data practices but heightened privacy concerns across collection, storage, and control, calling for better transparency and user controls.
-
Comparing Human Oversight Strategies for Computer-Use Agents
Oversight strategy in computer-use agents shapes exposure to problematic actions more reliably than correction success, with plan-based approaches reducing occurrences but not uniformly improving interventions.
-
Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents
A 3x3 between-subjects experiment finds that risk-contingent autonomy in LLM agents attenuates personalization's negative effects on privacy concerns and trust via increased perceived control.