Joint Hacking and Latent Hazard Rate Estimation

TL;DR

This paper introduces a hazard regression-based algorithm that predicts at-risk websites during hacking campaigns by modeling vulnerability evolution over time, achieving improved accuracy and interpretability.

Contribution

It presents a novel hazard regression model with time-varying coefficients and an efficient solution for predicting website risks and understanding vulnerability dynamics.

Findings

Outperforms classic methods in real data experiments.

Provides interpretable hazard rate estimates.

Efficiently infers vulnerability evolution over time.

Abstract

In this paper we describe an algorithm for predicting the websites at risk in a long range hacking activity, while jointly inferring the provenance and evolution of vulnerabilities on websites over continuous time. Specifically, we use hazard regression with a time-varying additive hazard function parameterized in a generalized linear form. The activation coefficients on each feature are continuous-time functions constrained with total variation penalty inspired by hacking campaigns. We show that the optimal solution is a 0th order spline with a finite number of adaptively chosen knots, and can be solved efficiently. Experiments on real data show that our method significantly outperforms classic methods while providing meaningful interpretability.