yonad2008/predict_gnn_gemma4_26b_gemma4_e4b

GNN Jailbreak Prediction Model (gemma4:26b+gemma4:e4b)

Homogeneous GNN classifier for unsafe/jailbreak likelihood in multi-turn conversations.

Evaluation Results

Metric	Value
F1	0.7113
PR-AUC	0.7991
ROC-AUC	0.9814
Precision	0.6911
Recall	0.7328
Best Threshold	0.610

Training Details

• Target model: gemma4:26b+gemma4:e4b
• Datasets: harmbench, harmful_behaviors_1
• Split column: goal
• Seed: 42
• Sentence model: sentence-transformers/all-MiniLM-L6-v2
• Hidden channels: 128
• Num layers: 2
• Dropout: 0.3

Dataset Size (training samples)

Prepared turn-level samples: 12548