Oct 13 · Tuesday

All papers

Found 1 paper

Filter5

System type

AI Agent12 coding agent7 Browser and computer use1 Multi-agent systems0

Attack surface / entry point

User input3 Web pages and interfaces1 Tool and skill descriptions0

System component

Monitors1 Permissions and sandboxing3 Vision3 Multimodal3

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.

System type：Browser and computer use System type：Multi-agent systems Attack surface / entry point：Web pages and interfaces Attack surface / entry point：Tool and skill descriptions System component：Monitors Clear all

Another 227papers do not have category tags yet and are not included in filtered results.

DefensesarXiv 2610.11942Oct 8
LGWM: Verifying GUI agent screen transitions with action-conditioned world models
Proposes LGWM, using an action-conditioned world model to verify GUI agent screen transitions.
arXiv
2610.11942
Published
Oct 8
Layer
Application layer
Setting
Browser and computer use
Evaluated models
LGWM
- DefensesMonitoring and auditing
- AttacksPrompt injection
- ComponentMonitors
Paper analysisRead analysis

You have reached the end

AI Safety Daily

Read the latest issueOne issue per day, updated as events develop

All papers

System type

Attack surface / entry point

System component

LGWM: Verifying GUI agent screen transitions with action-conditioned world models