ExploitMeter: Combining Fuzzing with Machine Learning for Automated Evaluation of Software Exploitability

摘要

Exploitable software vulnerabilities pose severe threats to its information security and privacy. Although a great amount of efforts have been dedicated to improving software security, research on quantifying software exploitability is still in its infancy. In this work, we propose ExploitMeter, a fuzzing-based framework of quantifying software exploitability that facilitates decision-making for software assurance and cyber insurance. Designed to be dynamic, efficient and rigorous, ExploitMeter integrates machine learning-based prediction and dynamic fuzzing tests in a Bayesian manner. Using 100 Linux applications, we conduct extensive experiments to evaluate the performance of ExploitMeter in a dynamic environment.