As society trusts more of its operations to autonomous systems, increasingly companies are making it a requirement that humans can understand how exactly a machine has reached a certain conclusion. The research efforts behind Explainable AI (XAI) is gaining traction as technology giants like Microsoft, Google and IBM, agree that AI should be to explain its decision making. XAI, sometimes called transparent AI, has the backing of the Defense Advanced Research Projects Agency (DARPA) an agency of the US Department of Defense, which is funding a large program develop the state of the art explainable AI techniques and modelling. Dr Brian Ruttenberg was formerly the senior scientist at Charles River Analytics (CRA) in Cambridge, where he was the principal investigator for CRA's effort on DARPA's XAI program. He argues XAI helps to identify bias or errors in algorithms and engenders trust in the technology.

"All you have to do is look at the attacks that have taken place recently--WannaCry, NotPetya and others--and see how quickly the industry and government is coming out and assigning responsibility to nation states such as North Korea, Russia and Iran," said Dmitri Alperovitch, chief technology officer at CrowdStrike Inc., a cybersecurity company that has investigated a number of state-sponsored hacks. The White House and other countries took roughly six months to blame North Korea and Russia for the WannaCry and NotPetya attacks, respectively, while it took about three years for U.S. authorities to indict a North Korean hacker for the 2014 attack against Sony . Forensic systems are gathering and analyzing vast amounts of data from digital databases and registries to glean clues about an attacker's infrastructure. These clues, which may include obfuscation techniques and domain names used for hacking, can add up to what amounts to a unique footprint, said Chris Bell, chief executive of Diskin Advanced Technologies, a startup that uses machine learning to attribute cyberattacks. Additionally, the increasing amount of data related to cyberattacks--including virus signatures, the time of day the attack took place, IP addresses and domain names--makes it easier for investigators to track organized hacking groups and draw conclusions about them.

Recent increases in computing power, coupled with rapid growth in the availability and quantity of data have rekindled our interest in the theory and applications of artificial intelligence (AI). However, for AI to be confidently rolled out by industries and governments, users want greater transparency through explainable AI (XAI) systems. The author introduces XAI concepts, and gives an overview of areas in need of further exploration--such as type-2 fuzzy logic systems--to ensure such systems can be fully understood and analyzed by the lay user.

After Dung's founding work in Abstract Argumentation Frameworks there has been a growing interest in extending the Dung's semantics in order to describe more complex or real life situations. Several of these approaches take the direction of weighted or probabilistic extensions. One of the most prominent probabilistic approaches is that of constellation Probabilistic Abstract Argumentation Frameworks from Li et al. In this paper, we present a normal form for constellation probabilistic abstract argumentation frameworks. Furthermore, we present a transformation from general constellation probabilistic abstract argumentation frameworks to the presented normal form. In this way we illustrate that the simpler normal form has equal representation power with the general one.

Artificial Intelligence (AI) approaches to problem-solving and decision-making are becoming more and more complex, leading to a decrease in the understandability of solutions. The European Union's new General Data Protection Regulation tries to tackle this problem by stipulating a "right to explanation" for decisions made by AI systems. One of the AI paradigms that may be affected by this new regulation is Answer Set Programming (ASP). Thanks to the emergence of efficient solvers, ASP has recently been used for problem-solving in a variety of domains, including medicine, cryptography, and biology. To ensure the successful application of ASP as a problem-solving paradigm in the future, explanations of ASP solutions are crucial. In this survey, we give an overview of approaches that provide an answer to the question of why an answer set is a solution to a given problem, notably off-line justifications, causal graphs, argumentative explanations and why-not provenance, and highlight their similarities and differences. Moreover, we review methods explaining why a set of literals is not an answer set or why no solution exists at all.

Weighted bipolar argumentation frameworks determine the strength of arguments based on an initial weight and the strength of their attackers and supporters. They find applications in decision support and social media analysis. Mossakowski and Neuhaus recently introduced a unification of different models and gave sufficient conditions for convergence and divergence in cyclic graphs. We build up on this work, incorporate additional models and extend results in several directions. In particular, we explain that the convergence guarantees can be seen as special cases of the contraction principle. We use this observation to unify and to generalize results and add runtime guarantees. Unfortunately, we find that guarantees obtained in this way are bought at the expense of open-mindedness, that is, the ability to move strength values away from the initial weights. However, we also demonstrate that divergence problems can be solved without giving up open-mindedness by continuizing the models. Finally, we integrate the Duality property that assures a symmetric impact of attack and support relations into the framework by Mossakowski and Neuhaus.

During last Wednesday's congressional hearing about Twitter transparency, Twitter CEO Jack Dorsey was forced to take accountability for the damaging cultural and political effects of his company. Soft-spoken and contrite, Dorsey provided a stark contrast to Facebook's Mark Zuckerberg, who seemed more confident when he appeared before Congress in April. In the months since, collective faith in the fabric of the internet has been anything but restored; instead, consumers, politicians, and the tech companies themselves continue to grapple with the aftermath of what social platforms hath wrought. During the hearing, Representative Debbie Dingell asked Dorsey if Twitter's algorithms are able to learn from the decisions they make--like who they suggest users follow, which tweets rise to the top, and in some cases what gets flagged for violating the platform's terms of service or even who gets banned--and also if Dorsey could explain how all of this works. "Great question," Dorsey responded, seemingly excited at a line of questioning that piqued his intellectual curiosity.

We study properties related to relevance in non-monotonic consequence relations obtained by systems of structured argumentation. Relevance desiderata concern the robustness of a consequence relation under the addition of irrelevant information. For an account of what (ir)relevance amounts to we use syntactic and semantic considerations. Syntactic criteria have been proposed in the domain of relevance logic and were recently used in argumentation theory under the names of non-interference and crash-resistance. The basic idea is that the conclusions of a given argumentative theory should be robust under adding information that shares no propositional variables with the original database. Some semantic relevance criteria are known from non-monotonic logic. For instance, cautious monotony states that if we obtain certain conclusions from an argumentation theory, we may expect to still obtain the same conclusions if we add some of them to the given database. In this paper we investigate properties of structured argumentation systems that warrant relevance desiderata.

Argumentation is a non-monotonic process. This reflects the fact that argumentation involves uncertain information, and so new information can cause a change in the conclusions drawn. However, the base logic does not need to be non-monotonic. Indeed, most proposals for structured argumentation use a monotonic base logic (e.g. some form of modus ponens with a rule-based language, or classical logic). Nonetheless, there are issues in capturing defeasible reasoning in argumentation including choice of base logic and modelling of defeasible knowledge. And there are insights and tools to be harnessed for research in non-monontonic logics. We consider some of these issues in this paper.

The increasing incorporation of Artificial Intelligence in the form of automated systems into decision-making procedures highlights not only the importance of decision theory for automated systems but also the need for these decision procedures to be explainable to the people involved in them. Traditional realist accounts of explanation, wherein explanation is a relation that holds (or does not hold) eternally between an explanans and an explanandum, are not adequate to account for the notion of explanation required for artificial decision procedures. We offer an alternative account of explanation as used in the context of automated decision-making that makes explanation an epistemic phenomenon, and one that is dependent on context. This account of explanation better accounts for the way that we talk about, and use, explanations and derived concepts, such as `explanatory power', and also allows us to differentiate between reasons or causes on the one hand, which do not need to have an epistemic aspect, and explanations on the other, which do have such an aspect. Against this theoretical backdrop we then review existing approaches to explanation in Artificial Intelligence and Machine Learning, and suggest desiderata which truly explainable decision systems should fulfill.