A number of measures for quantifying information leakage of a program have been proposed. Most of these measures evaluate a program as a whole by quantifying how much information can be leaked on average by different program outputs. While these measures perfectly fit for static program analyses, they cannot be used by dynamic analyses since they do not specify what information an attacker learns through observing one concrete program output. In this paper we study the existing definitions of quantitative information flow. Our goal is to find the definition of dynamic leakage – it should evaluate how much information an attacker learns when she observes one program output. Surprisingly, we find out that none of the existing definitions provide a suitable measure for dynamic leakage. We hence open a new research question in quantitative information flow area: which definition of dynamic leakage is suitable?