A Robust Estimator for Evaluating Internet Worm Infection Rate

Abstract

The Internet worm is a menace for the security of the Internet users. To detect and protect the Internet worm becomes an important research topic in the field of Internet security. A robust estimation method for evaluating worm infection rate is proposed in this paper. The robust estimator of worm infection rate is derived based on the robust maximum likelihood estimation principle at first; The corresponding elements of the equivalent weight matrix constructed by the residuals and some chosen weight functions are given; The error influence functions related to the robust estimator and the least squares estimator are respectively analyzed; At last, a simulated example is carried out. It is shown that the robust estimation is effective and reliable in resisting the bad influence of the outlying scan data on the estimated worm infection rate with high computation convergence speed.