wazer24/group_2_v_b_model_deployment

How wazer24/group_2_v_b_model_deployment works

This repository is a malware concept-drift research project: it compares static classifiers with a latent Neural ODE on chronologically split malware features, then reports metrics and visualizations. The main experiment path runs from feature data through temporal preparation, model training, and shared evaluation. A separate Streamlit dashboard presents research results and architecture/ablation material. The tree and excerpts support the experiment’s core call paths; dashboard links to generated artifacts are not shown, so it is represented independently.

Main entry points: train_ode.py Neural ODE training · chronology.py Temporal splits · train_baselines.py Static baselines · results Experiment metrics

Components 13

Data preparation

Malware features
Drift ranking dataset/feature_drift_ranking.csv
Temporal splits src/chronology.py

Model experiments

Static baselines src/train_baselines.py
Neural ODE training src/train_ode.py
ODE architecture src/ode_model.py

Evaluation and analysis

Shared evaluation src/evaluate.py
Experiment metrics notebooks/results
Metric visualizations src/visualize.py
Deliverable figures src/generate_deliverable_graphs.py

Research presentation

Research dashboard malware-concept-drift-dashboard/app.py

Other components

Researcher
Dashboard user

Connections 14

Malware features → Temporal splits: loads features src/chronology.py
Drift ranking → Temporal splits: selects features src/chronology.py
Temporal splits → Static baselines: provides splits src/train_baselines.py
Temporal splits → Neural ODE training: provides splits src/train_ode.py
Static baselines → Shared evaluation: evaluates predictions src/train_baselines.py
Neural ODE training → Shared evaluation: evaluates predictions src/train_ode.py
Neural ODE training → ODE architecture: trains model src/train_ode.py
Static baselines → Experiment metrics: writes metrics src/train_baselines.py
Neural ODE training → Experiment metrics: writes metrics src/train_ode.py
Experiment metrics → Metric visualizations: reads metrics src/visualize.py
Researcher → Static baselines: runs experiments
Researcher → Neural ODE training: runs experiments
Researcher → Deliverable figures: generates figures
Dashboard user → Research dashboard: views research

Drawn by GitDiagram on November 12, 2026 from the repository's file tree, README and source files. Read as Markdown ·