The concept of explainability is envisioned to satisfy society's demands for transparency on machine learning decisions. The concept is simple: like humans, algorithms should explain the rationale behind their decisions so that their fairness can be assessed. While this approach is promising in a local context (e.g. to explain a model during debugging at training time), we argue that this reasoning cannot simply be transposed in a remote context, where a trained model by a service provider is only accessible through its API. This is problematic as it constitutes precisely the target use-case requiring transparency from a societal perspective. Through an analogy with a club bouncer (which may provide untruthful explanations upon customer reject), we show that providing explanations cannot prevent a remote service from lying about the true reasons leading to its decisions. More precisely, we prove the impossibility of remote explainability for single explanations, by constructing an attack on explanations that hides discriminatory features to the querying user. We provide an example implementation of this attack. We then show that the probability that an observer spots the attack, using several explanations for attempting to find incoherences, is low in practical settings. This undermines the very concept of remote ex-plainability in general. 1 Introduction Modern decision-making driven by black-box systems now impacts a significant share of our lives [9, 29]. Those systems build on user data, and range from rec-ommenders [21] ( e.g., for personalized ranking of information on websites) to predictive algorithms ( e.g., credit default) [29]. This widespread deployment, along with the opaque decision process provided by those systems raises concerns about transparency for the general public or for policy makers [12]. This translated in some jurisdictions ( e.g., United States of America and Europe) into a so called right to explanation [12, 26], that states that the output decisions of an algorithm must be motivated. Explainability of in-house models An already large body of work is interested in the explainability of implicit machine learning models (such as neural network models) [2, 13, 20]. Indeed, those models show state-of-art performances when it comes to a task accuracy, but they are not designed to provide explanations -or at least intelligible decision processes-when one wants to obtain more than the output decision of the model. In the context of recommendation, the expression "post hoc explanation" has been coined [32].

Fortnite: Battle Royale got a new item today, and it's a weird one. The bouncer is mostly like the directional bounce pads of yore, but it's a little out of place in the way the game works now. You place it like a trap, and either friends or foes bounce off of it with no fall damage. It has its uses, to be sure, and both streamers and top-level players will no doubt figure out the tactical ins and outs of using the new item. For most players it's a curiosity at best, or like the recently added shopping carts, just something to have fun with: a far cry from the Light Machine Gun.

They are not quite the directional bounce pads that we used to have in the game, but they sure are similar. A new "bouncer" item is coming to Fortnite: Battle Royale, first uncovered by dataminers @Diebuddies and now confirmed by the in-game news feed. It's a placed environmental object akin to a jump pad or trap, and it will have at least one important gameplay function. Place this pad for a big bounce boost – no fall damage! No fall damage is most certainly the key here.

In exactly 12 months, Britain will leave the European Union. It's a troubling time for the island state as politicians squabble over exit conditions and citizens grapple with a deep divide in their economic, societal and cultural values. For many, the future seems bleak, but it shouldn't compare to the one found in Not Tonight, an upcoming video game by Tiki Taka Soccer developer Panic Barn. In this alternate version of Britain, one ruled by an extreme right-wing government, you're forced to work as a bouncer that gets paid for identifying and turning away European citizens. It's a horrific job, but one that's necessary to pay the bills and keep your British citizenship.