Artificial intelligence (AI) systems in high-stakes domains raise concerns about proxy discrimination, unfairness, and explainability. Existing audits often fail to reveal why unfairness arises, particularly when rooted in structural bias. We propose a novel framework using formal abductive explanations to explain proxy discrimination in individual AI decisions. Leveraging background knowledge, our method identifies which features act as unjustified proxies for protected attributes, revealing hidden structural biases. Central to our approach is the concept of aptitude, a task-relevant property independent of group membership, with a mapping function aligning individuals of equivalent aptitude across groups to assess fairness substantively. As a proof of concept, we showcase the framework with examples taken from the German credit dataset, demonstrating its applicability in real-world cases.

With the rise of fifth-generation (5G) networks in critical applications, it is urgent to move from detection of malicious activity to systems capable of providing a reliable verdict suitable for mitigation. In this regard, understanding and interpreting machine learning (ML) models' security alerts is crucial for enabling actionable incident response orchestration. Explainable Artificial Intelligence (XAI) techniques are expected to enhance trust by providing insights into why alerts are raised. A dominant approach statistically associates feature sets that can be correlated to a given alert. This paper starts by questioning whether such attribution is relevant for future generation communication systems, and investigates its merits in comparison with an approach based on logical explanations. We extensively study two methods, SHAP and VoTE-XAI, by analyzing their interpretations of alerts generated by an XGBoost model in three different use cases with several 5G communication attacks. We identify three metrics for assessing explanations: sparsity, how concise they are; stability, how consistent they are across samples from the same attack type; and efficiency, how fast an explanation is generated. As an example, in a 5G network with 92 features, 6 were deemed important by VoTE-XAI for a Denial of Service (DoS) variant, ICMPFlood, while SHAP identified over 20. More importantly, we found a significant divergence between features selected by SHAP and VoTE-XAI. However, none of the top-ranked features selected by SHAP were missed by VoTE-XAI. When it comes to efficiency of providing interpretations, we found that VoTE-XAI is significantly more responsive, e.g. it provides a single explanation in under 0.002 seconds, in a high-dimensional setting (478 features).

Reasoning about unpredicted change consists in explaining observations by events; we propose here an approach for explaining time-stamped observations by surprises, which are simple events consisting in the change of the truth value of a fluent. A framework for dealing with surprises is defined. Minimal sets of surprises are provided together with time intervals where each surprise has occurred, and they are characterized from a model-based diagnosis point of view. Then, a probabilistic approach of surprise minimisation is proposed.

Support Vector Classifier (SVC) is a well-known Machine Learning (ML) model for linear classification problems. It can be used in conjunction with a reject option strategy to reject instances that are hard to correctly classify and delegate them to a specialist. This further increases the confidence of the model. Given this, obtaining an explanation of the cause of rejection is important to not blindly trust the obtained results. While most of the related work has developed means to give such explanations for machine learning models, to the best of our knowledge none have done so for when reject option is present. We propose a logic-based approach with formal guarantees on the correctness and minimality of explanations for linear SVCs with reject option. We evaluate our approach by comparing it to Anchors, which is a heuristic algorithm for generating explanations. Obtained results show that our proposed method gives shorter explanations with reduced time cost. Keywords: Logic-based explainable AI Support vector machines Classification with reject option.

Deep neural networks (DNNs) are increasingly being used as controllers in reactive systems. However, DNNs are highly opaque, which renders it difficult to explain and justify their actions. To mitigate this issue, there has been a surge of interest in explainable AI (XAI) techniques, capable of pinpointing the input features that caused the DNN to act as it did. Existing XAI techniques typically face two limitations: (i) they are heuristic, and do not provide formal guarantees that the explanations are correct; and (ii) they often apply to ``one-shot'' systems, where the DNN is invoked independently of past invocations, as opposed to reactive systems. Here, we begin bridging this gap, and propose a formal DNN-verification-based XAI technique for reasoning about multi-step, reactive systems. We suggest methods for efficiently calculating succinct explanations, by exploiting the system's transition constraints in order to curtail the search space explored by the underlying verifier. We evaluate our approach on two popular benchmarks from the domain of automated navigation; and observe that our methods allow the efficient computation of minimal and minimum explanations, significantly outperforming the state of the art. We also demonstrate that our methods produce formal explanations that are more reliable than competing, non-verification-based XAI techniques.

The ability to explain why a machine learning model arrives at a particular prediction is crucial when used as decision support by human operators of critical systems. The provided explanations must be provably correct, and preferably without redundant information, called minimal explanations. In this paper, we aim at finding explanations for predictions made by tree ensembles that are not only minimal, but also minimum with respect to a cost function. To this end, we first present a highly efficient oracle that can determine the correctness of explanations, surpassing the runtime performance of current state-of-the-art alternatives by several orders of magnitude when computing minimal explanations. Secondly, we adapt an algorithm called MARCO from related works (calling it m-MARCO) for the purpose of computing a single minimum explanation per prediction, and demonstrate an overall speedup factor of two compared to the MARCO algorithm which enumerates all minimal explanations. Finally, we study the obtained explanations from a range of use cases, leading to further insights of their characteristics. In particular, we observe that in several cases, there are more than 100,000 minimal explanations to choose from for a single prediction. In these cases, we see that only a small portion of the minimal explanations are also minimum, and that the minimum explanations are significantly less verbose, hence motivating the aim of this work.

With the rapid growth of machine learning, deep neural networks (DNNs) are now being used in numerous domains. Unfortunately, DNNs are "black-boxes", and cannot be interpreted by humans, which is a substantial concern in safety-critical systems. To mitigate this issue, researchers have begun working on explainable AI (XAI) methods, which can identify a subset of input features that are the cause of a DNN's decision for a given input. Most existing techniques are heuristic, and cannot guarantee the correctness of the explanation provided. In contrast, recent and exciting attempts have shown that formal methods can be used to generate provably correct explanations. Although these methods are sound, the computational complexity of the underlying verification problem limits their scalability; and the explanations they produce might sometimes be overly complex. Here, we propose a novel approach to tackle these limitations. We (1) suggest an efficient, verification-based method for finding minimal explanations, which constitute a provable approximation of the global, minimum explanation; (2) show how DNN verification can assist in calculating lower and upper bounds on the optimal explanation; (3) propose heuristics that significantly improve the scalability of the verification process; and (4) suggest the use of bundles, which allows us to arrive at more succinct and interpretable explanations. Our evaluation shows that our approach significantly outperforms state-of-the-art techniques, and produces explanations that are more useful to humans. We thus regard this work as a step toward leveraging verification technology in producing DNNs that are more reliable and comprehensible.

Abductive forgetting is removing variables from a logical formula while maintaining its abductive explanations. It is defined in either of two ways, depending on its intended application. Both differ from the usual forgetting, which maintains consequences rather than explanations. Differently from that, abductive forgetting from a propositional formula may not be expressed by any propositional formula. A necessary and sufficient condition tells when it is. Checking this condition is \P{3}-complete, and is in \P{4} if minimality of explanations is required. A way to guarantee expressibility of abductive forgetting is to switch from propositional to default logic. Another is to introduce new variables.

Abduction is a form of reasoning where assumptions are made to explain observations. For example, if an agent were to observe that some light was not working, it can hypothesize what is happening in the world to explain why the light was not working. An intelligent tutoring system could try to explain why a student gives some answer in terms of what the student understands and does not understand. The term abduction was coined by Peirce (1839-1914) to differentiate this type of reasoning from deduction, which involves determining what logically follows from a set of axioms, and induction, which involves inferring general relationships from examples. In abduction, an agent hypothesizes what may be true about an observed case.

ABox abduction plays an important role in reasoning over description logic (DL) ontologies. However, it does not work with inconsistent DL ontologies. To tackle this problem while achieving tractability, we generalize ABox abduction from the classical semantics to an inconsistency-tolerant semantics, namely the Intersection ABox Repair (IAR) semantics, and propose the notion of IAR-explanations in inconsistent DL ontologies. We show that computing all minimal IAR-explanations is tractable in data complexity for first-order rewritable ontologies. However, the computational method may still not be practical due to a possibly large number of minimal IAR-explanations. Hence we propose to use preference information to reduce the number of explanations to be computed.