Countering Large-Scale Malicious Multiagent Systems by Consensus Breakdown Based on Critical Node Identification

Multiagent systems (MASs) can be exploited for malicious activities, which pose significant threats to public safety and national security. While current literature has explored countermeasures for individual or several agents, these approaches are inadequate for large-scale malicious MASs due to the lack of a systematic, global perspective. Additionally, the heterogeneity of MASs, wherein agents exhibit varying system weights, necessitates a strategy that prioritizes agents with high system weight to maximize disruption. To address these challenges, a consensus breakdown algorithm based on critical node identification and network topology decomposition is proposed. The proposed algorithm decomposes the network topology of both large-scale homogeneous and heterogeneous MASs by disabling critical nodes, thereby splitting MASs into multiple smaller agent clusters and preventing MASs from achieving global consensus. In scenarios involving both homogeneous and heterogeneous MASs, this approach transforms the critical node identification problem into a node regression problem. The algorithm leverages GraphSAGE, a highly efficient graph neural network (GNN) with a sampling mechanism, making it well-suited for feature extraction in large-scale networks while addressing potential computational constraints common in real-world applications. Relying on the sampling mechanism, GraphSAGE enhances computational efficiency when processing large-scale network topologies. To better fit the need for consensus breakdown, the information dissemination capabilities of nodes are considered when defining node importance. Furthermore, to extend the algorithm to the scenarios of heterogeneous MASs where agents have different system weights, the node importance is combined with the system weight of each agent to determine the final node criticality. Extensive simulation results validate the superior performance of the proposed algorithm across various aspects. Comparative experiments further demonstrate the accuracy and efficiency of the algorithm.