Localization of False Data Injection Attacks in Power Grid Based on Adaptive Neighborhood Selection and Spatio-Temporal Feature Fusion

False Data Injection Attacks (FDIAs) pose a critical security threat to modern power grids, corrupting state estimation and enabling malicious control actions that can lead to severe consequences, including cascading failures, large-scale blackouts, and significant economic losses. While detecting attacks is important, accurately localizing compromised nodes or measurements is even more critical, as it enables timely mitigation, targeted response, and enhanced system resilience beyond what detection alone can offer. Existing research typically models topological features using fixed structures, which can introduce irrelevant information and affect the effectiveness of feature extraction. To address this limitation, this paper proposes an FDIA localization model with adaptive neighborhood selection, which dynamically captures spatial dependencies of the power grid by adjusting node relationships based on data-driven similarities. The improved Transformer is employed to pre-fuse global spatial features of the graph, enriching the feature representation. To improve spatio-temporal correlation extraction for FDIA localization, the proposed model employs dilated causal convolution with a gating mechanism combined with graph convolution to capture and fuse long-range temporal features and adaptive topological features. This fully exploits the temporal dynamics and spatial dependencies inherent in the power grid. Finally, multi-source information is integrated to generate highly robust node embeddings, enhancing FDIA detection and localization. Experiments are conducted on IEEE 14, 57, and 118-bus systems, and the results demonstrate that the proposed model substantially improves the accuracy of FDIA localization. Additional experiments are conducted to verify the effectiveness and robustness of the proposed model.