Abstract: The communication link of wireless sensor networks (WSNs) is not as private and controllable as wired network, and its robustness is not strong in the face of false endorsement insertion attacks (FEIAs). In view of this, this paper combines the genetic algorithm and fuzzy theory, and proposes an adaptive defense scheme (ACS). Aiming at the problem that ACS scheme was prone to misjudge FEIAs, this paper focused on the selection of safety parameters. And this scheme was simulated. The simulation results show that compared with the traditional ACS scheme, the combined defense algorithm reduces the storage requirements and computational complexity, improves the detection accuracy, and can be effectively implemented by a single WSN model, so as to realize the adaptive optimization of fuzzy system.