F-BLEAU is a tool for estimating the leakage of a system about its secrets in a black-box manner (i.e., by only looking at examples of secret inputs and respective outputs). It considers a generic system as a black-box, taking secret inputs and returning outputs accordingly, and it measures how much the outputs "leak" about the inputs.
F-BLEAU is based on the equivalence between estimating the error of a Machine Learning model of a specific class and the estimation of information leakage [1,2,3].
This code was also used for the experiments of  on the following evaluations: Gowalla, e-passport, and side channel attack to finite field exponentiation.
F-BLEAU is thought to be mainly used via the binary it provides,
For usage instructions, please refer to
fbleau's home page
or to the help screen:
For the library documentation, please refer to the appropriate links within this page.
 2017, "Bayes, not Naïve: Security Bounds on Website Fingerprinting Defenses". Giovanni Cherubin
 2018, "F-BLEAU: Practical Channel Leakage Estimation". Giovanni Cherubin, Konstantinos Chatzikokolakis, Catuscia Palamidessi.
 (Blog) "Machine Learning methods for Quantifying the Security of Black-boxes". https://giocher.com/pages/bayes.html
This module implements Bayes risk estimates, and heuristics for evaluating convergence.