Networked systems are playing an indispensable role in modern society, and their robustness is considered as a critical research issue. As a major threat to the network robustness, cascading failures have attracted increasing attention. To tackle the problem of incomplete topological information, we use the link prediction methods to restore the missing information of the networks first, and then utilize the predicted information to further help to distinguish the critical nodes in the network systems from the attacker\'s perspective. Simulation results on both synthetic and real-world networks have demonstrated the effectiveness of the proposed method.