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.

From self-driving vehicles and back-flipping robots to virtual assistants who book our next appointment at the hair salon or at that restaurant for dinner - machine learning systems are becoming increasingly ubiquitous. The main reason for this is that these methods boast remarkable predictive capabilities. However, most of these models remain black boxes, meaning that it is very challenging for humans to follow and understand their intricate inner workings. Consequently, interpretability has suffered under this ever-increasing complexity of machine learning models. Especially with regards to new regulations, such as the General Data Protection Regulation (GDPR), the necessity for plausibility and verifiability of predictions made by these black boxes is indispensable. Driven by the needs of industry and practice, the research community has recognised this interpretability problem and focussed on developing a growing number of so-called explanation methods over the past few years. These methods explain individual predictions made by black box machine learning models and help to recover some of the lost interpretability. With the proliferation of these explanation methods, it is, however, often unclear, which explanation method offers a higher explanation quality, or is generally better-suited for the situation at hand. In this thesis, we thus propose an axiomatic framework, which allows comparing the quality of different explanation methods amongst each other. Through experimental validation, we find that the developed framework is useful to assess the explanation quality of different explanation methods and reach conclusions that are consistent with independent research.

We study invariant local expansion operators for conflict-free and admissible sets in Abstract Argumentation Frameworks (AFs). Such operators are directly applied on AFs, and are invariant with respect to a chosen "semantics" (that is w.r.t. each of the conflict free/admissible set of arguments). Accordingly, 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.

Companies like to flaunt their use of artificial intelligence to the point where it's virtually meaningless, but the truth is that AI as we know it is still quite dumb. While it can generate useful results, it can't explain why it produced those results in meaningful terms, or adapt to ever-evolving situations. DARPA thinks it can move AI forward, thoug. It's launching an Artificial Intelligence Exploration program that will invest in new AI concepts, including "third wave" AI with contextual adaptation and an ability to explain its decisions in ways that make sense. If it identified a cat, for instance, it could explain that it detected fur, paws and whiskers in a familiar cat shape. Importantly, DARPA also hopes to step up the pace.

This paper addresses the semantics of weighted argumentation graphs that are bipolar, i.e. contain both attacks and supports for arguments. We build on previous work by Amgoud, Ben-Naim et. al. We study the various characteristics of acceptability semantics that have been introduced in these works. We provide a simplified and mathematically elegant formulation of these characteristics. The formulation is modular because it cleanly separates aggregation of attacking and supporting arguments (for a given argument a) from the computation of their influence on a's initial weight. We discuss various semantics for bipolar argumentation graphs in the light of these characteristics. Based on the modular framework, we prove general convergence and divergence theorems. We show that all semantics converge for all acyclic graphs and that no sum-based semantics can converge for all graphs. In particular, we show divergence of Euler-based semantics for certain cyclic graphs. We also provide the first semantics for bipolar weighted graphs that converges for all graphs.

Computational tools to support this through proof checking, automatic theorem proving, and computer algebra are well-established, though they require formal, computationally explicit, content as input. However, the existing mathematical literature, particularly informal mathematical dialogues, and expository texts, is opaque to such systems, which cannot currently handle the variety of activities typically involved in producing such knowledge and proofs, such as, for example, exposition and argument that concerns making conjectures, forming concepts, and discussing examples and counterexamples. Our goal is to bridge this gap through devising an expressive modelling language that is closely related to the way mathematics is actually done. Our approach to modelling such content is inspired by the general-purpose argument modelling formalism Inference Anchoring Theory (IAT), introduced by Reed and Budzynska (2010). As its name suggests, IAT anchors logical inferences in discourse. IAT has been applied to mediation (Janier and Reed, 2017), debates (Budzynska et al, 2014b), and to paradoxes in ethotic argumentation (Budzynska, 2013), along with other real-world dialogues (Budzynska et al, 2013).

Logical Glue is the leading cloud based predictive analytics platform for the insurance sector. We use Explainable Artificial Intelligence (XAI) to deliver actionable insight to insurers, in order to improve profitability. The power of XAI means being able to understand the reasons why decisions have been made in the form of human-interpretable rules, allowing better internal communication between technical and business users, and an improved experience for customers. We partner with insurers, re-insurers and MGAs to predict, automate and improve areas along the entire customer journey such as quote conversion, risk pricing, claims process optimisation, and customer retention. The time to value for these benefits have been realised in a matter of weeks not months, I would be delighted to talk through some of our use cases in more detail, to learn more please contact Naveed Ashraf on naveed.ashraf@logicalglue.com

The Defense Advanced Research Projects Agency (DARPA) recently launched the Explainable Artificial Intelligence (XAI) program that aims to create a suite of new AI techniques that enable end users to understand, appropriately trust, and effectively manage the emerging generation of AI systems. In this paper, inspired by DARPA's XAI program, we propose a new paradigm in security research: Explainable Security (XSec). We discuss the ``Six Ws'' of XSec (Who? What? Where? When? Why? and How?) and argue that XSec has unique and complex characteristics: XSec involves several different stakeholders (i.e., the system's developers, analysts, users and attackers) and is multi-faceted by nature (as it requires reasoning about system model, threat model and properties of security, privacy and trust as well as about concrete attacks, vulnerabilities and countermeasures). We define a roadmap for XSec that identifies several possible research directions.