To deal with Byzantine attacks in 5G cognitive radio networks, a bilateral threshold selection-based algorithm is proposed in the spectrum sensing process. In each round, secondary uses ( SUs ) first submit the energy values and instantaneous detection signal-to-noise ratios ( SNRs ) to the fusion center ( FC ) . According to detection SNRs, the FC conducts normalization calculations on the energy values. Then, the FC makes a sort operation for these normalized energy values and traverses all the possible mid-points between these sorted normalized energy values to maximize the classification accuracy of each SU. Finally, by introducing the recognition probability and misclassification probability, the distributions of the normalized energy values are analyzed and the bilateral threshold of classification accuracy is obtained via a target misclassification probability. Hence, the blacklist of malicious secondary users ( MSUs ) is obtained. Simulation results show that the proposed scheme outperforms the current mainstream schemes in correct sensing probability, false alarm probability and detection probability.