ALT Since the right to explanation as defined in current regulations (Goodman & Flaxman, 2017) does not give precise directives on what it means to provide a “valid explanation” (Wachter et al., 2017; Edwards & Veale, 2017), there is a legal loophole that can be used by dishonest companies to cover up the possible unfairness of their black-box models by providing misleading explanations. In particular, due to the growing

ALT as promoting the false perception that the learning models used by the company are fair while it might not be so. In this paper, our main objective is to raise the awareness of this issue, which we believe to be a serious concern related to the use of black-box explanation. In addition, to provide concrete evidence on this possible risk, we show that it is possible to forge a fairer explanation from a truly unfair bl