As distributed terminals are increasingly integrated into modern power systems with high penetration of renewable energy and decentralized resources, access control mechanisms must support continuous and highly detailed trust assessment. Existing approaches based on machine learning primarily rely on network traffic features from a single source and analyze terminals in isolation, which limits their ability to capture complex device states and correlated attack behaviors. This paper presents a trust assessment framework for distributed power grid terminals that combines multidimensional behavioral modeling with dual domain graph neural networks. Behavioral features are collected from network traffic, runtime environment, and hardware or kernel events and are fused into compact representations through a variational autoencoder to mitigate redundancy and reduce computational overhead. Based on the fused features and observed communication relationships, two graphs are constructed in parallel: a feature domain graph reflecting behavioral similarity and a topological domain graph capturing communication structure between terminals. Graph convolution is performed in both domains to jointly model individual behavioral risk and correlation across terminals. A fusion mechanism based on attention is further introduced to adaptively integrate embeddings specific to each domain, together with a loss function that enforces both shared and complementary representations across domains. Experiments conducted on the CIC EV Charger Attack Dataset 2024 show that the proposed framework achieves a classification accuracy of 96.84%, while maintaining a recall rate above 95% for the low trust category. These results indicate that incorporating multidimensional behavior perception and dual domain relational modeling improves trust assessment performance for distributed power grid terminals under complex attack scenarios.
Consistency checking across independently developed implementations of the same industrial control protocol provides an effective signal for defect discovery because an implementation whose response deviates from the majority under identical inputs is more likely to contain faults or robustness issues. However, existing consistency checking methods remain difficult to apply to complex stateful protocols in practice, since sequence dependencies can cause error propagation, large test suites incur high execution cost across multiple implementations, and inconsistent outputs are costly to triage. This paper proposes ConDiffFuzz, a dependency-aware and dynamically adjusted hierarchical consistency checking method for industrial control protocol implementations. ConDiffFuzz analyzes dependencies among check sequences to optimize execution order and dynamically prunes and regenerates dependent sequences after failures to mitigate inconsistency error propagation. The checking process derives implementation-specific finite state machines and inconsistency records, which further support focused differential fuzzing, parallel execution across multiple implementations, and log-based anomaly triage. Experiments on five Modbus over Modbus/TCP implementations show that ConDiffFuzz achieves a test case acceptance rate of 86.00%, increases average path coverage to 74.46%, improves the average number of triggered anomalies by 12.28%, and reduces the false-positive rate by 20.94% compared with four representative baseline fuzzers (SPIKE, BooFuzz, PeachFuzzer, and Kitty).