AI Paper Atlas

Research map / Large language models / AI and society

Mental Model-based Generation of Lies for Insider Threat Modeling

Brittany Cates, Sarath Sreedharan

AAAI 2026 · Large language models › AI and society · approach: Data commons and human baselines · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
provide a lie that explains the longer path to the supervisorinsider-threat robot · user study (42 participants)participants stopping the robot: 16 of 21 stopped -> 1 of 21 stoppedImproved
compute attack pair (lie plus plan) instead of plain optimal planplanning · IPC domains (kappa=5)planning time: 0.62 -> 0.73 s (Grid World)No clear effect
compute attack pair instead of plain optimal planplanning · Gripperplanning time: 0.61 -> 1.21 sHurt
increase grid sizeattack-pair search · GridWorldminimum kappa: 1.00 -> 1.53 (3x3 -> 7x7)No clear effect
increase distance of real goal from optimal pathattack-pair search · GridWorldlie count: 0.17 -> 1 (distance 1 -> 4)Hurt
increase grid sizeattack-pair search · GridWorldlie count: correlation 0.405No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy