An explainable assistant for multiuser privacy

Abstract Multiuser Privacy (MP) concerns the protection of personal information in situations where such is co-owned by multiple users. MP particularly problematic collaborative platforms as online social networks (OSN). In fact, too often OSN users experience privacy violations due to conflicts generated other sharing content that involves them without their permission. Previous studies show most cases could be avoided, and are mainly difficulty for uploader select appropriate policies. For this reason, we present ELVIRA, first fully explainable assistant collaborates with ELVIRA agents identify optimal policy a collectively owned content. An extensive evaluation agent through software simulations two user suggests thanks its properties being role-agnostic, adaptive, both utility- value-driven, would more successful at supporting than approaches presented literature terms (i) trade-off between utility promotion moral values, (ii) users’ satisfaction explained recommended output.