yonad2008's picture
Upload GNN turn-level model artifacts
2c69dbe verified
metadata
language: en
tags:
  - gnn
  - jailbreak-detection
  - text-classification
model-index:
  - name: predict_gnn_phi4_14b
    results:
      - task:
          type: text-classification
          name: Jailbreak Detection
        metrics:
          - name: F1
            type: f1
            value: 0.9411
          - name: PR-AUC
            type: pr_auc
            value: 0.9782
          - name: ROC-AUC
            type: roc_auc
            value: 0.9593
          - name: Precision
            type: precision
            value: 0.9682
          - name: Recall
            type: recall
            value: 0.9163

GNN Jailbreak Prediction Model (phi4:14b)

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

Evaluation Results

Metric Value
F1 0.9411
PR-AUC 0.9782
ROC-AUC 0.9593
Precision 0.9682
Recall 0.9163
Best Threshold 0.270

Training Details

  • Target model: phi4:14b
  • 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: 707