🔒 LLM Security Benchmark

Testing AI Security Analysis Against Deceptive Code Patterns

📊 Latest Benchmark Results

Comprehensive Security Benchmark Report

Complete analysis of LLM performance against deceptive security vulnerabilities, including model comparisons, technique effectiveness, and statistical analysis.

View Full Report

📚 Documentation

🖼️ Visualizations

Explore the benchmark visualizations:

Model Performance

Model Performance Comparison

Technique Effectiveness

Technique Effectiveness Heatmap

🔗 View Project on GitHub