In view of the drawbacks of the traditional filtering methods, such as poor anti-interference ability and low convergence, a new adaptive nonlinear filtering method in ad hoc network communication with narrowband interference is proposed. The MLMS method is introduced and the filter structure is given. The nonlinear error function is used to process the estimated error signal, and the tap factor is updated by MLMS method. In order to reduce the interference of the signal interference sample, the nonlinear function is used to correct it, and a new updating equation of the tap factor is given. According to sinusoidal interference, the Gauss noise signal is described, and the optimum tap factor is obtained. The performance of the proposed method against narrowband interference is evaluated by means of the ratio of the output signal-to-noise ratio to the input signal-to-noise ratio. The proposed method is applied to narrowband interference communication in ad hoc networks, and the results show that the proposed method has strong anti-interference ability, high convergence performance and good signal effect.