How Machine Learning and Semantic Embeddings Reorder CVE Vulnerabilities Beyond Raw CVSS Scores

def visualize_results(df, priority_scores, feature_importance):
   fig, axes = plt.subplots(2, 3, figsize=(18, 10))
   fig.suptitle('Vulnerability Scanner - ML Analysis Dashboard', fontsize=16, fontweight="bold")
   axes[0, 0].hist(priority_scores, bins=30, color="crimson", alpha=0.7, edgecolor="black")
   axes[0, 0].set_xlabel('Priority Score')
   axes[0, 0].set_ylabel('Frequency')
   axes[0, 0].set_title('Priority Score Distribution')
   axes[0, 0].axvline(np.percentile(priority_scores, 75), color="orange", linestyle="--", label="75th percentile")
   axes[0, 0].legend()
   axes[0, 1].scatter(df['cvss_score'], priority_scores, alpha=0.6, c=priority_scores, cmap='RdYlGn_r', s=50)
   axes[0, 1].set_xlabel('CVSS Score')
   axes[0, 1].set_ylabel('ML Priority Score')
   axes[0, 1].set_title('CVSS vs ML Priority')
   axes[0, 1].plot([0, 10], [0, 1], 'k--', alpha=0.3)
   severity_counts = df['severity'].value_counts()
   colors = {'CRITICAL': 'darkred', 'HIGH': 'red', 'MEDIUM': 'orange', 'LOW': 'yellow'}
   axes[0, 2].bar(severity_counts.index, severity_counts.values, color=[colors.get(s, 'gray') for s in severity_counts.index])
   axes[0, 2].set_xlabel('Severity')
   axes[0, 2].set_ylabel('Count')
   axes[0, 2].set_title('Severity Distribution')
   axes[0, 2].tick_params(axis="x", rotation=45)
   top_features = feature_importance.head(10)
   axes[1, 0].barh(top_features['feature'], top_features['importance'], color="steelblue")
   axes[1, 0].set_xlabel('Importance')
   axes[1, 0].set_title('Top 10 Feature Importance')
   axes[1, 0].invert_yaxis()
   if 'cluster' in df.columns:
       cluster_counts = df['cluster'].value_counts().sort_index()
       axes[1, 1].bar(cluster_counts.index, cluster_counts.values, color="teal", alpha=0.7)
       axes[1, 1].set_xlabel('Cluster')
       axes[1, 1].set_ylabel('Count')
       axes[1, 1].set_title('Vulnerability Clusters')
   attack_vector_counts = df['attack_vector'].value_counts()
   axes[1, 2].pie(attack_vector_counts.values, labels=attack_vector_counts.index, autopct="%1.1f%%", startangle=90)
   axes[1, 2].set_title('Attack Vector Distribution')
   plt.tight_layout()
   plt.show()


def main():
   print("="*70)
   print("AI-ASSISTED VULNERABILITY SCANNER WITH ML PRIORITIZATION")
   print("="*70)
   print()
   fetcher = CVEDataFetcher()
   df = fetcher.fetch_recent_cves(days=30, max_results=50)
   print(f"Dataset Overview:")
   print(f"  Total CVEs: {len(df)}")
   print(f"  Date Range: {df['published'].min()[:10]} to {df['published'].max()[:10]}")
   print(f"  Severity Breakdown: {df['severity'].value_counts().to_dict()}")
   print()
   feature_extractor = VulnerabilityFeatureExtractor()
   embeddings = feature_extractor.extract_semantic_features(df['description'].tolist())
   df = feature_extractor.extract_keyword_features(df)
   df = feature_extractor.encode_categorical_features(df)
   prioritizer = VulnerabilityPrioritizer()
   X = prioritizer.prepare_features(df, embeddings)
   severity_map = {'LOW': 0, 'MEDIUM': 1, 'HIGH': 2, 'CRITICAL': 3, 'UNKNOWN': 1}
   y_severity = df['severity'].map(severity_map).values
   y_score = df['cvss_score'].values
   X_scaled = prioritizer.train_models(X, y_severity, y_score)
   priority_scores, severity_probs, score_preds = prioritizer.predict_priority(X)
   df['ml_priority_score'] = priority_scores
   df['predicted_score'] = score_preds
   analyzer = VulnerabilityAnalyzer(n_clusters=5)
   clusters = analyzer.cluster_vulnerabilities(embeddings)
   df = analyzer.analyze_clusters(df, clusters)
   feature_imp, emb_imp = prioritizer.get_feature_importance()
   print(f"\n--- Feature Importance ---")
   print(feature_imp.head(10))
   print(f"\nAverage embedding importance: {emb_imp:.4f}")
   print("\n" + "="*70)
   print("TOP 10 PRIORITY VULNERABILITIES")
   print("="*70)
   top_vulns = df.nlargest(10, 'ml_priority_score')[['cve_id', 'cvss_score', 'ml_priority_score', 'severity', 'description']]
   for idx, row in top_vulns.iterrows():
       print(f"\n{row['cve_id']} [Priority: {row['ml_priority_score']:.3f}]")
       print(f"  CVSS: {row['cvss_score']:.1f} | Severity: {row['severity']}")
       print(f"  {row['description'][:100]}...")
   print("\n\nGenerating visualizations...")
   visualize_results(df, priority_scores, feature_imp)
   print("\n" + "="*70)
   print("ANALYSIS COMPLETE")
   print("="*70)
   print(f"\nResults summary:")
   print(f"  High Priority (>0.7): {(priority_scores > 0.7).sum()} vulnerabilities")
   print(f"  Medium Priority (0.4-0.7): {((priority_scores >= 0.4) & (priority_scores <= 0.7)).sum()}")
   print(f"  Low Priority (<0.4): {(priority_scores < 0.4).sum()}")
   return df, prioritizer, analyzer


if __name__ == "__main__":
   results_df, prioritizer, analyzer = main()
   print("\n✓ All analyses completed successfully!")
   print("\nYou can now:")
   print("  - Access results via 'results_df' DataFrame")
   print("  - Use 'prioritizer' to predict new vulnerabilities")
   print("  - Explore 'analyzer' for clustering insights")