pygip.models.attack.Realistic

Classes

DGLEdgePredictor(*args, **kwargs)	DGL version of edge prediction module
DGLSurrogateModel(*args, **kwargs)	DGL version of surrogate model
RealisticAttack(dataset, attack_node_fraction)	DGL-based GNN model extraction attack

class pygip.models.attack.Realistic.DGLEdgePredictor(*args: Any, **kwargs: Any)

Bases: Module

DGL version of edge prediction module

forward(graph, features)

predict_edges(node_embeddings, node_pairs)

Predict edge existence probability

class pygip.models.attack.Realistic.DGLSurrogateModel(*args: Any, **kwargs: Any)

Bases: Module

DGL version of surrogate model

forward(graph, features)

class pygip.models.attack.Realistic.RealisticAttack(dataset, attack_node_fraction, model_path=None, hidden_dim=64, threshold_s=0.7, threshold_a=0.5)

Bases: BaseAttack

DGL-based GNN model extraction attack

_abc_impl = <_abc_data object>

add_potential_edges(candidate_edges, labeled_nodes)

Add potential edges based on edge prediction results

attack()

Execute model extraction attack

compute_cosine_similarity(features)

Compute cosine similarity of node features

evaluate_attack(enhanced_graph)

Evaluate attack performance

generate_candidate_edges(labeled_nodes, unlabeled_nodes)

Generate candidate edge set

simulate_target_model_queries(query_nodes, error_rate=0.15)

Simulate target model queries with a certain proportion of incorrect labels

supported_api_types = {'dgl'}

supported_datasets = {}

train_edge_predictor(labeled_nodes, predicted_labels, epochs=100)

Train edge prediction model

train_surrogate_model(enhanced_graph, labeled_nodes, predicted_labels, epochs=200)

Train surrogate model