The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
Who to Trust in Multi-Robot Systems: Joint Robot and Object Hypothesis Trust Inference via Neural-Symbolic Cross-Validation
- Published
- Record updated
Summary
NeST-Bayes is a neural-symbolic framework that jointly infers trust in robots and object hypotheses in multi-robot systems, using only inter-robot observation consistency rather than preassigned trust, reputation or side-channel identity signals. Trust evidence from ego-centric relational graphs is accumulated over time via Bayesian updates of Beta-distributed beliefs. Under aggressive optimized attacks it reports 98.8% robot precision with 93.8% recall and 98.3% object precision with 95.4% recall, and in an occlusion-rich Webots warehouse 92.5% robot precision and 97.3% object precision.