Find confidence interval in bivariate kernel estimation using ksdensity

I'm executing this piece of code in order to estimate the probability density function of a bivariate set of random points:

x = [0+.5*rand(20,1) 5+2.5*rand(20,1);
      .75+.25*rand(10,1) 8.75+1.25*rand(10,1)];

figure
ksdensity(x);

and I wonder how to use the informations coming from the Matlab function ksdensity to evaluate the confidence interval I need.

My goal is to find outliers points in the set, namely that points that fall over the confidence interval.

[Matteo Mastropierro]

Hi Daniele, I have the same problem, have you found a solution to it?Thank you.