GNN Jailbreak Prediction Model (gemma4:e4b)

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

Evaluation Results

Metric Value
F1 0.8937
PR-AUC 0.9358
ROC-AUC 0.9513
Precision 0.9589
Recall 0.8379
Best Threshold 0.750

Training Details

  • Target model: gemma4:e4b
  • Datasets: harmbench
  • 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: 425

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Evaluation results