Abstract. Lately, several works have analyzed potential uses of argumentation in multi-party debates. Usually, the focus of such works is the computation of a collectively "correct" outcome, a challenging task even when the debate's users truthfully express their beliefs. This work focuses on debates where some users may exhibit specific types of "malicious" behavior: they may lie (by making statements they do not believe to hold) and they may hide valuable information (by not making relevant statements they believe to hold). Our approach is the following: firstly, we define "user attributes" which capture different aspects of a user's behavior in a debate (how active, how opinionated and how classifiable a user has been); then, we build and test experimentally hypotheses that, from the values of these attributes, can predict whether a user has lied and/or hidden valuable information.