SentinelAC began as a commercial anti-cheat system for FiveM. That project has concluded. The research and public source releases are now collected on the SentinelAC Research website.
AIICD
AI Internal-Cheat Detection examines short sequences of cursor movement for signs of internal cheat-menu use. A Temporal CNN processes the sequence, and XGBoost combines its representation with motion statistics to produce a score for review.
The public release includes the FiveM collection resource, a Python inference service, model artifacts, and documentation. The training dataset is not included.
Cursor behavior is indirect evidence. AIICD is experimental and should not be the sole basis for permanent punishment. The model card explains its limitations.
Public source releases
AIICD and the SentinelAC Open Source Edition are available under MIT licenses. These releases have a defined scope. The original private infrastructure is not included.
Read the research archive for architecture notes and project background.