We present distributed self-organized model for collaboration of multiple heterogeneous IDS sensors. The adaptation model is based on a game-theoretical approach that optimizes the behavior of each IDS node with respect to other nodes in highly dynamic environment. We performed initial experimental evaluation of the proposed collaboration model on two autonomous IDS detectors deployed on different parts of university network. We show that this Intrusion Detection Network significantly improves the detection effectiveness and brings advanced defensive mechanism against novel highly sophisticated threats.