Human-machine teaming in medical AI requires us to understand to what degree a trained clinician should weigh AI predictions. While previous work has shown the potential of AI assistance at improving clinical predictions, existing clinical decision support systems either provide no explainability of their predictions or use techniques like saliency and Shapley values, which do not allow for physician-based verification. To address this gap, this study compares previously used explainable AI techniques with a newly proposed technique termed '2-factor retrieval (2FR)', which is a combination of interface design and search retrieval that returns similarly labeled data without processing this data. This results in a 2-factor security blanket where: (a) correct images need to be retrieved by the AI; and (b) humans should associate the retrieved images with the current pathology under test. We find that when tested on chest X-ray diagnoses, 2FR leads to increases in clinician accuracy, with particular improvements when clinicians are radiologists and have low confidence in their decision. Our results highlight the importance of understanding how different modes of human-AI decision making may impact clinician accuracy in clinical decision support systems.

Recent developments in the field of explainable artificial intelligence (XAI) for vision models investigate the information extracted by their feature encoder. We contribute to this effort and propose Neuro-Activated Vision Explanations (NAVE), which extracts the information captured by the encoder by clustering the feature activations of the frozen network to be explained. The method does not aim to explain the model's prediction but to answer questions such as which parts of the image are processed similarly or which information is kept in deeper layers. Experimentally, we leverage NAVE to show that the training dataset and the level of supervision affect which concepts are captured. In addition, our method reveals the impact of registers on vision transformers (ViT) and the information saturation caused by the watermark Clever Hans effect in the training set.

We study the problem of finding optimal sparse, manifold-aligned counterfactual explanations for classifiers. Canonically, this can be formulated as an optimization problem with multiple non-convex components, including classifier loss functions and manifold alignment (or \emph{plausibility}) metrics. The added complexity of enforcing \emph{sparsity}, or shorter explanations, complicates the problem further. Existing methods often focus on specific models and plausibility measures, relying on convex $\ell_1$ regularizers to enforce sparsity. In this paper, we tackle the canonical formulation using the accelerated proximal gradient (APG) method, a simple yet efficient first-order procedure capable of handling smooth non-convex objectives and non-smooth $\ell_p$ (where $0 \leq p < 1$) regularizers. This enables our approach to seamlessly incorporate various classifiers and plausibility measures while producing sparser solutions. Our algorithm only requires differentiable data-manifold regularizers and supports box constraints for bounded feature ranges, ensuring the generated counterfactuals remain \emph{actionable}. Finally, experiments on real-world datasets demonstrate that our approach effectively produces sparse, manifold-aligned counterfactual explanations while maintaining proximity to the factual data and computational efficiency.

As machine learning becomes more widespread and is used in more critical applications, it's important to provide explanations for these models, to prevent unintended behavior. Unfortunately, many current interpretability methods struggle with faithfulness. Therefore, this Ph.D. thesis investigates the question "How to provide and ensure faithful explanations for complex general-purpose neural NLP models?" The main thesis is that we should develop new paradigms in interpretability. This is achieved by first developing solid faithfulness metrics and then applying the lessons learned from this investigation to develop new paradigms. The two new paradigms explored are faithfulness measurable models (FMMs) and self-explanations. The idea in self-explanations is to have large language models explain themselves, we identify that current models are not capable of doing this consistently. However, we suggest how this could be achieved. The idea of FMMs is to create models that are designed such that measuring faithfulness is cheap and precise. This makes it possible to optimize an explanation towards maximum faithfulness, which makes FMMs designed to be explained. We find that FMMs yield explanations that are near theoretical optimal in terms of faithfulness. Overall, from all investigations of faithfulness, results show that post-hoc and intrinsic explanations are by default model and task-dependent. However, this was not the case when using FMMs, even with the same post-hoc explanation methods. This shows, that even simple modifications to the model, such as randomly masking the training dataset, as was done in FMMs, can drastically change the situation and result in consistently faithful explanations. This answers the question of how to provide and ensure faithful explanations.

The use of machine learning (ML) in critical domains such as medicine poses risks and requires regulation. One requirement is that decisions of ML systems in high-risk applications should be human-understandable. The field of "explainable artificial intelligence" (XAI) seemingly addresses this need. However, in its current form, XAI is unfit to provide quality control for ML; it itself needs scrutiny. Popular XAI methods cannot reliably answer important questions about ML models, their training data, or a given test input. We recapitulate results demonstrating that popular XAI methods systematically attribute importance to input features that are independent of the prediction target. This limits their utility for purposes such as model and data (in)validation, model improvement, and scientific discovery. We argue that the fundamental reason for this limitation is that current XAI methods do not address well-defined problems and are not evaluated against objective criteria of explanation correctness. Researchers should formally define the problems they intend to solve first and then design methods accordingly. This will lead to notions of explanation correctness that can be theoretically verified and objective metrics of explanation performance that can be assessed using ground-truth data.

Phishing has been a prevalent cyber threat that manipulates users into revealing sensitive private information through deceptive tactics, designed to masquerade as trustworthy entities. Over the years, proactively detection of phishing URLs (or websites) has been established as an widely-accepted defense approach. In literature, we often find supervised Machine Learning (ML) models with highly competitive performance for detecting phishing websites based on the extracted features from both phishing and benign (i.e., legitimate) websites. However, it is still unclear if these features or indicators are dependent on a particular dataset or they are generalized for overall phishing detection. In this paper, we delve deeper into this issue by analyzing two publicly available phishing URL datasets, where each dataset has its own set of unique and overlapping features related to URL string and website contents. We want to investigate if overlapping features are similar in nature across datasets and how does the model perform when trained on one dataset and tested on the other. We conduct practical experiments and leverage explainable AI (XAI) methods such as SHAP plots to provide insights into different features' contributions in case of phishing detection to answer our primary question, "Can features for phishing URL detection be trusted across diverse dataset?". Our case study experiment results show that features for phishing URL detection can often be dataset-dependent and thus may not be trusted across different datasets even though they share same set of feature behaviors.

We investigate the effectiveness of Explainable AI (XAI) in verifying Machine Unlearning (MU) within the context of harbor front monitoring, focusing on data privacy and regulatory compliance. With the increasing need to adhere to privacy legislation such as the General Data Protection Regulation (GDPR), traditional methods of retraining ML models for data deletions prove impractical due to their complexity and resource demands. MU offers a solution by enabling models to selectively forget specific learned patterns without full retraining. We explore various removal techniques, including data relabeling, and model perturbation. Then, we leverage attribution-based XAI to discuss the effects of unlearning on model performance. Our proof-of-concept introduces feature importance as an innovative verification step for MU, expanding beyond traditional metrics and demonstrating techniques' ability to reduce reliance on undesired patterns. Additionally, we propose two novel XAI-based metrics, Heatmap Coverage (HC) and Attention Shift (AS), to evaluate the effectiveness of these methods. This approach not only highlights how XAI can complement MU by providing effective verification, but also sets the stage for future research to enhance their joint integration.

Explaining the decision-making processes of Artificial Intelligence (AI) models is crucial for addressing their "black box" nature, particularly in tasks like image classification. Traditional eXplainable AI (XAI) methods typically rely on unimodal explanations, either visual or textual, each with inherent limitations. Visual explanations highlight key regions but often lack rationale, while textual explanations provide context without spatial grounding. Further, both explanation types can be inconsistent or incomplete, limiting their reliability. To address these challenges, we propose a novel Multimodal Explanation-Guided Learning (MEGL) framework that leverages both visual and textual explanations to enhance model interpretability and improve classification performance. Our Saliency-Driven Textual Grounding (SDTG) approach integrates spatial information from visual explanations into textual rationales, providing spatially grounded and contextually rich explanations. Additionally, we introduce Textual Supervision on Visual Explanations to align visual explanations with textual rationales, even in cases where ground truth visual annotations are missing. A Visual Explanation Distribution Consistency loss further reinforces visual coherence by aligning the generated visual explanations with dataset-level patterns, enabling the model to effectively learn from incomplete multimodal supervision. We validate MEGL on two new datasets, Object-ME and Action-ME, for image classification with multimodal explanations. Experimental results demonstrate that MEGL outperforms previous approaches in prediction accuracy and explanation quality across both visual and textual domains. Our code will be made available upon the acceptance of the paper.

Effective communication is essential in collaborative tasks, so AI-equipped robots working alongside humans need to be able to explain their behaviour in order to cooperate effectively and earn trust. We analyse and classify communications among human participants collaborating to complete a simulated emergency response task. The analysis identifies messages that relate to various kinds of interactive explanations identified in the explainable AI literature. This allows us to understand what type of explanations humans expect from their teammates in such settings, and thus where AI-equipped robots most need explanation capabilities. We find that most explanation-related messages seek clarification in the decisions or actions taken. We also confirm that messages have an impact on the performance of our simulated task.

There is a growing need to understand how digital systems can support clinical decision-making, particularly as artificial intelligence (AI) models become increasingly complex and less human-interpretable. This complexity raises concerns about trustworthiness, impacting safe and effective adoption of such technologies. Improved understanding of decision-making processes and requirements for explanations coming from decision support tools is a vital component in providing effective explainable solutions. This is particularly relevant in the data-intensive, fast-paced environments of intensive care units (ICUs). To explore these issues, group interviews were conducted with seven ICU clinicians, representing various roles and experience levels. Thematic analysis revealed three core themes: (T1) ICU decision-making relies on a wide range of factors, (T2) the complexity of patient state is challenging for shared decision-making, and (T3) requirements and capabilities of AI decision support systems. We include design recommendations from clinical input, providing insights to inform future AI systems for intensive care.