Preprint
Aug 2026
Online Learning in Stackelberg Security Games with Adaptive Attacker Sequences and Time-Varying Attack Intensities
An extended security game is formulated in which an attacker may select multiple targets and derive an exact mixed-integer linear programming oracle under a optimistic tie-breaking rule to study no-regret online learning in Repeated Stackelberg Security Games with time-varying attack intensities.
Guan-Da Chen, Shi-Heng Zhang, Yue Wang et al.
· 0 citations