erroristotle/dvdr_llmFramework de ensemble para detecção e correção de vulnerabilidades de software usando múltiplos modelos de linguagem de grande porte, com análise de consenso e ferramentas de avaliação para trade-offs entre precisão e recall.
Implementação oficial e artefato para o artigo de pesquisa:
"DVDR-LLM: Quando LLMs são Melhores em Conjunto para Detecção e Correção de Vulnerabilidades de Software?"
O DVDR-LLM é um framework de ensemble que examina sistematicamente as compensações fundamentais na agregação de múltiplos Modelos de Linguagem de Grande Porte (LLMs) para detecção e correção de vulnerabilidades de software. Nossa avaliação abrangente revela insights críticos sobre o equilíbrio precisão-revocação, os benefícios da diversidade de modelos e as abordagens baseadas em consenso em aplicações críticas de segurança.
DVDR_LLM/
├── dvdr_llm/ # Main package (professional structure)
│ ├── __init__.py # Package exports
│ ├── cli.py # Command-line interface
│ ├── config.py # Configuration settings
│ ├── core/ # Core functionality
│ │ ├── api_client.py # LLM API communication
│ │ ├── detector.py # VulnerabilityDetector class
│ │ └── prompts.py # Prompt generation utilities
│ ├── analysis/ # Analysis modules
│ │ ├── consensus.py # Consensus analysis
│ │ └── metrics.py # Performance metrics
│ ├── evaluation/ # Model evaluation
│ │ └── evaluator.py # ModelEvaluator class
│ ├── visualization/ # Plotting and visualization
│ │ └── plotter.py # ResultsPlotter class
│ └── tools/ # Additional utilities
├── utils/ # Original utility modules
│ ├── api.py # LLM API interaction helpers
│ ├── database.py # SQLite helper functions
│ └── config.py # Configuration constants
├── data/ # Datasets and databases
│ ├── vulnerabilities.csv # Vulnerability data
│ └── vulnerable and patched codes.sqlite
├── output/ # Generated results and databases
│ ├── database_*.sqlite # Model-specific databases
│ ├── consensus_analysis/ # Consensus analysis results
│ ├── metrics/ # Performance metrics
│ └── database_exports/ # Exported data
├── examples/ # Usage examples
│ └── basic_usage.py # Basic usage demonstration
├── docs/ # Documentation
│ └── README_consensus_analysis.md
├── paper/ # Research paper
│ ├── main.pdf # Published paper
│ └── main.tex # LaTeX source
├── setup.py # Package installation
├── requirements.txt # Dependencies
├── CHANGELOG.md # Change log
├── LICENSE # MIT License
└── README.md # This file
Clone o repositório:
git clone https://github.com/Erroristotle/DVDR_LLM.git
cd DVDR_LLM
Instale as dependências:
pip install -r requirements.txt
pip install -e . # Install package in development mode
Verifique a instalação:
python verify_package.py
# Run vulnerability detection with ensemble
dvdr-llm detect --models llama3-8b,codellama-7b --database data/vulnerabilities.sqlite
# Analyze consensus patterns (RQ2)
dvdr-llm analyze consensus --input results/metrics/model_predictions.csv --threshold 0.6
# Generate conflict pattern visualization (Figure in paper)
python dvdr_llm/visualization/conflict_pattern_plot.py results/metrics/reviewer_insights_disagreement_patterns.csv -o reviewer_insights
# Evaluate ensemble performance across abstraction levels (RQ3)
dvdr-llm evaluate --models-dir output/ --abstraction-analysis
from dvdr_llm import VulnerabilityDetector, ConsensusAnalyzer, ModelEvaluator
# Initialize vulnerability detector
detector = VulnerabilityDetector("llama3-8b-instruct")
# Connect to database
detector.connect_to_database("data/vulnerabilities.sqlite")
# Analyze code for vulnerabilities
code = """
void vulnerable_function(char *input) {
char buffer[100];
strcpy(buffer, input); // Buffer overflow
}
"""
# Get CVE predictions
cve_names = detector.analyze_code_for_cves(code, 2023)
print(f"Identified CVEs: {cve_names}")
# Detect vulnerability
is_vulnerable = detector.detect_vulnerability(code)
print(f"Is vulnerable: {is_vulnerable}")
# Process database entries
stats = detector.process_database_entries(limit=100)
print(f"Processed {stats['processed']} entries")
# Clean up
detector.close()
# Multi-model consensus analysis
model_databases = {
"llama3-8b": "output/database_llama3-8b-instruct.sqlite",
"codellama-7b": "output/database_codellama-7b-instruct.sqlite",
"gemma2-9b": "output/database_gemma2-9b.sqlite"
}
analyzer = ConsensusAnalyzer()
consensus_results = analyzer.run_full_analysis(model_databases)
# Model evaluation
evaluator = ModelEvaluator()
evaluation_results = evaluator.evaluate_multiple_models(
model_databases,
"data/ground_truth.csv"
)
# Generate Table 2 (Model comparison with delta percentages)
python dvdr_llm/tools/model_contribution_analysis.py results/metrics/model_predictions.csv --compare-ensemble --threshold 0.7
# Analyze individual vs ensemble performance
dvdr-llm evaluate --comparison-analysis --threshold 0.7
# Generate Figure 3 (Threshold sensitivity analysis)
python dvdr_llm/tools/threshold_analysis.py results/metrics/model_predictions.csv --range 0.3-0.8
# Statistical validation of threshold selection
python dvdr_llm/analysis/statistical_validation.py --threshold-analysis
# Generate Table 3 (Abstraction level analysis)
python dvdr_llm/evaluation/evaluator.py --abstraction-analysis --threshold 0.6
# Level-specific performance evaluation
dvdr-llm evaluate --abstraction-levels 1,2,3 --ensemble
# Analyze patch quality metrics (ROUGE, CodeBLEU, Complexity)
python dvdr_llm/tools/patch_quality_analysis.py results/patches/ --weighted-scoring
# Generate Figure 4 (Patch similarity and complexity analysis)
dvdr-llm visualize --patch-analysis --metrics results/patch_metrics.csv
# Main conflict pattern analysis figure (Figure 2)
python dvdr_llm/visualization/conflict_pattern_plot.py results/metrics/reviewer_insights_disagreement_patterns.csv -o reviewer_insights