The first consideration when discussing transparency in AI should be data, the fuel that powers the algorithms. Companies should disclose where and how they got the data they used to fuel their AI systems' decisions. Consumers should own their data and should be privy to the myriad ways that businesses use and sell such information, which is often done without clear and conscious consumer consent. Because data is the foundation for all AI, it is valid to want to know where the data comes from and how it might explain biases and counterintuitive decisions that AI systems make. On the algorithmic side, grandstanding by IBM and other tech giants around the idea of "explainable AI" is nothing but virtue signaling that has no basis in reality.

There has recently been a surge of work in explanatory artificial intelligence (XAI). This research area tackles the important problem that complex machines and algorithms often cannot provide insights into their behavior and thought processes. XAI allows users and parts of the internal system to be more transparent, providing explanations of their decisions in some level of detail. These explanations are important to ensure algorithmic fairness, identify potential bias/problems in the training data, and to ensure that the algorithms perform as expected. However, explanations produced by these systems is neither standardized nor systematically assessed. In an effort to create best practices and identify open challenges, we provide our definition of explainability and show how it can be used to classify existing literature. We discuss why current approaches to explanatory methods especially for deep neural networks are insufficient. Finally, based on our survey, we conclude with suggested future research directions for explanatory artificial intelligence.

Artificial intelligence (AI) shifts the computing paradigm from rule-based programming to an outcome-based approach. It allows processes to operate at scale, reducing the number of human processing errors, and inventing new ways of solving problems. AlphaGo inspired Go players to try new strategies after experts had been using the same opening moves for 3,000 years. As adoption increases, AI will enable organizations to unlock the "last mile" that traditional automation could not address. But as more enterprises entrust AI to make decisions on their behalf, governance becomes super critical.

The recent years have witnessed the rise of accurate but obscure decision systems which hide the logic of their internal decision processes to the users. The lack of explanations for the decisions of black box systems is a key ethical issue, and a limitation to the adoption of machine learning components in socially sensitive and safety-critical contexts. In this paper we focus on the problem of black box outcome explanation, i.e., explaining the reasons of the decision taken on a specific instance. We propose LORE, an agnostic method able to provide interpretable and faithful explanations. LORE first leans a local interpretable predictor on a synthetic neighborhood generated by a genetic algorithm. Then it derives from the logic of the local interpretable predictor a meaningful explanation consisting of: a decision rule, which explains the reasons of the decision; and a set of counterfactual rules, suggesting the changes in the instance's features that lead to a different outcome. Wide experiments show that LORE outperforms existing methods and baselines both in the quality of explanations and in the accuracy in mimicking the black box.

There has been a recent resurgence in the area of explainable artificial intelligence as researchers and practitioners seek to make their algorithms more understandable. Much of this research is focused on explicitly explaining decisions or actions to a human observer, and it should not be controversial to say that looking at how humans explain to each other can serve as a useful starting point for explanation in artificial intelligence. However, it is fair to say that most work in explainable artificial intelligence uses only the researchers' intuition of what constitutes a `good' explanation. There exists vast and valuable bodies of research in philosophy, psychology, and cognitive science of how people define, generate, select, evaluate, and present explanations, which argues that people employ certain cognitive biases and social expectations towards the explanation process. This paper argues that the field of explainable artificial intelligence should build on this existing research, and reviews relevant papers from philosophy, cognitive psychology/science, and social psychology, which study these topics. It draws out some important findings, and discusses ways that these can be infused with work on explainable artificial intelligence.

On May 25, 2018, the General Data Protection Regulation (GDPR) comes into effect across the EU, requiring sweeping changes to how organizations handle personal data. And GDPR standards have real teeth: For most violations, organizations have to pay a penalty of up to €20 million or 4 percent of global revenue, whichever is greater. With the Cambridge Analytica scandal fresh on people's minds, many hope that GDPR will become a model for a new standard of data privacy around the world. We've already heard some industry leaders calling for Facebook to apply GDPR standards to its business in non-EU countries, even though the law doesn't require it. But privacy is only one aspect of the debate around the use of data-driven systems.

Recent use includes the assassination with VX of Kim Jong Nam, half-brother of North Korean leader Kim Jong Un, in Kuala Lumpur airport in February 2017 and the attempted murder of Sergei Skripal, a 66-year-old former Russian double agent, and his daughter with a Novichok nerve agent in March in England.

The assignment of weights to attacks in a classical Argumentation Framework allows to compute semantics by taking into account the different importance of each argument. We represent a Weighted Argumentation Framework by a non-binary matrix, and we characterize the basic extensions (such as w-admissible, w-stable, w-complete) by analysing sub-blocks of this matrix. Also, we show how to reduce the matrix into another one of smaller size, that is equivalent to the original one for the determination of extensions. Furthermore, we provide two algorithms that allow to build incrementally w-grounded and w-preferred extensions starting from a w-admissible extension.

We study invariant local expansion operators for admissible sets in Abstract Argumentation Frameworks (AFs). Accordingly, we introduce in the future work section also the invariant local expansion for conflict free sets and we derive a definition of robustness for AFs in terms of the number of times such operators can be applied without producing any change in the chosen semantics.

Argumentative persuasion usually employs one of the three persuasion strategies: Ethos, Pathos or Logos. Several approaches have been proposed to model persuasive agents, however, none of them explored how the choice of a strategy impacts the mental states of the debaters and the argumentation process. We conducted a field experiment with real debaters to assess the impact of the mental engagement and emotions of the participants, as well as of the persuasiveness power of the arguments exchanged during the debate. Our results show that the Pathos strategy is the most effective in terms of mental engagement.