Research Papers

In the world of medical diagnostics, the adoption of various deep learning techniques is quite common as well as effective, and its statement is equally true when it comes to implementing it into the retina Optical Coherence Tomography (OCT) sector, but (i)These techniques have the black box characteristics that prevent the medical professionals to completely trust the results generated from them (ii)Lack of precision of these methods restricts their implementation in clinical and complex cases (iii)The existing works and models on the OCT classification are substantially large and complicated and they require a considerable amount of memory and computational power, reducing the quality of classifiers in real-time applications. To meet these problems, in this paper a self-developed CNN model has been proposed which is comparatively smaller and simpler along with the use of Lime that introduces Explainable AI to the study and helps to increase the interpretability of the model. This addition will be an asset to the medical experts for getting major and detailed information and will help them in making final decisions and will also reduce the opacity and vulnerability of the conventional deep learning models.

Explaining deep learning of galaxy morphology with saliency mapping

Prabh Bhambra, Benjamin Joachimi, Ofer Lahav

We successfully demonstrate the use of explainable artificial intelligence (XAI) techniques on astronomical datasets in the context of measuring galactic bar lengths. The method consists of training convolutional neural networks on human classified data from Galaxy Zoo in order to predict general galaxy morphologies, and then using SmoothGrad (a saliency mapping technique) to extract the bar for measurement by a bespoke algorithm. We contrast this to another method of using a convolutional neural network to directly predict galaxy bar lengths. These methods achieved correlation coefficients of 0.76 and 0.59, and root mean squared errors of 1.69 and 2.10 respective to human measurements. We conclude that XAI methods outperform conventional deep learning in this case, which could be reasonably explained by the larger datasets available when training the models. We suggest that our XAI method can be used to extract other galactic features (such as the bulge-to-disk ratio) without needing to collect new datasets or train new models. We also suggest that these techniques can be used to refine deep learning models as well as identify and eliminate bias within training datasets.

Trustworthy Artificial Intelligence and Process Mining: Challenges and Opportunities

Andrew Pery, Majid Rafiei, Michael Simon +1

The premise of this paper is that compliance with Trustworthy AI governance best practices and regulatory frameworks is an inherently fragmented process spanning across diverse organizational units, external stakeholders, and systems of record, resulting in process uncertainties and in compliance gaps that may expose organizations to reputational and regulatory risks. Moreover, there are complexities associated with meeting the specific dimensions of Trustworthy AI best practices such as data governance, conformance testing, quality assurance of AI model behaviors, transparency, accountability, and confidentiality requirements. These processes involve multiple steps, hand-offs, re-works, and human-in-the-loop oversight. In this paper, we demonstrate that process mining can provide a useful framework for gaining fact-based visibility to AI compliance process execution, surfacing compliance bottlenecks, and providing for an automated approach to analyze, remediate and monitor uncertainty in AI regulatory compliance processes.

Ultrasound is a non-invasive imaging modality that can be conveniently used to classify suspicious breast nodules and potentially detect the onset of breast cancer. Recently, Convolutional Neural Networks (CNN) techniques have shown promising results in classifying ultrasound images of the breast into benign or malignant. However, CNN inference acts as a black-box model, and as such, its decision-making is not interpretable. Therefore, increasing effort has been dedicated to explaining this process, most notably through GRAD-CAM and other techniques that provide visual explanations into inner workings of CNNs. In addition to interpretation, these methods provide clinically important information, such as identifying the location for biopsy or treatment. In this work, we analyze how adversarial assaults that are practically undetectable may be devised to alter these importance maps dramatically. Furthermore, we will show that this change in the importance maps can come with or without altering the classification result, rendering them even harder to detect. As such, care must be taken when using these importance maps to shed light on the inner workings of deep learning. Finally, we utilize Multi-Task Learning (MTL) and propose a new network based on ResNet-50 to improve the classification accuracies. Our sensitivity and specificity is comparable to the state of the art results.

On the Importance of Domain-specific Explanations in AI-based Cybersecurity Systems (Technical Report)

Jose N. Paredes, Juan Carlos L. Teze, Gerardo I. Simari +1

With the availability of large datasets and ever-increasing computing power, there has been a growing use of data-driven artificial intelligence systems, which have shown their potential for successful application in diverse areas. However, many of these systems are not able to provide information about the rationale behind their decisions to their users. Lack of understanding of such decisions can be a major drawback, especially in critical domains such as those related to cybersecurity. In light of this problem, in this paper we make three contributions: (i) proposal and discussion of desiderata for the explanation of outputs generated by AI-based cybersecurity systems; (ii) a comparative analysis of approaches in the literature on Explainable Artificial Intelligence (XAI) under the lens of both our desiderata and further dimensions that are typically used for examining XAI approaches; and (iii) a general architecture that can serve as a roadmap for guiding research efforts towards the development of explainable AI-based cybersecurity systems -- at its core, this roadmap proposes combinations of several research lines in a novel way towards tackling the unique challenges that arise in this context.

Artificial Intelligence (AI) systems are being deployed around the globe in critical fields such as healthcare and education. In some cases, expert practitioners in these domains are being tasked with introducing or using such systems, but have little or no insight into what data these complex systems are based on, or how they are put together. In this paper, we consider an AI system from the domain practitioner's perspective and identify key roles that are involved in system deployment. We consider the differing requirements and responsibilities of each role, and identify a tension between transparency and privacy that needs to be addressed so that domain practitioners are able to intelligently assess whether a particular AI system is appropriate for use in their domain.

The task of detecting morphed face images has become highly relevant in recent years to ensure the security of automatic verification systems based on facial images, e.g. automated border control gates. Detection methods based on Deep Neural Networks (DNN) have been shown to be very suitable to this end. However, they do not provide transparency in the decision making and it is not clear how they distinguish between genuine and morphed face images. This is particularly relevant for systems intended to assist a human operator, who should be able to understand the reasoning. In this paper, we tackle this problem and present Focused Layer-wise Relevance Propagation (FLRP). This framework explains to a human inspector on a precise pixel level, which image regions are used by a Deep Neural Network to distinguish between a genuine and a morphed face image. Additionally, we propose another framework to objectively analyze the quality of our method and compare FLRP to other DNN interpretability methods. This evaluation framework is based on removing detected artifacts and analyzing the influence of these changes on the decision of the DNN. Especially, if the DNN is uncertain in its decision or even incorrect, FLRP performs much better in highlighting visible artifacts compared to other methods.

Towards Analogy-Based Explanations in Machine Learning

Eyke Hüllermeier

Principles of analogical reasoning have recently been applied in the context of machine learning, for example to develop new methods for classification and preference learning. In this paper, we argue that, while analogical reasoning is certainly useful for constructing new learning algorithms with high predictive accuracy, is is arguably not less interesting from an interpretability and explainability point of view. More specifically, we take the view that an analogy-based approach is a viable alternative to existing approaches in the realm of explainable AI and interpretable machine learning, and that analogy-based explanations of the predictions produced by a machine learning algorithm can complement similarity-based explanations in a meaningful way. To corroborate these claims, we outline the basic idea of an analogy-based explanation and illustrate its potential usefulness by means of some examples.

Natural Language Interaction with Explainable AI Models

Arjun R Akula, Sinisa Todorovic, Joyce Y Chai +1

This paper presents an explainable AI (XAI) system that provides explanations for its predictions. The system consists of two key components -- namely, the prediction And-Or graph (AOG) model for recognizing and localizing concepts of interest in input data, and the XAI model for providing explanations to the user about the AOG's predictions. In this work, we focus on the XAI model specified to interact with the user in natural language, whereas the AOG's predictions are considered given and represented by the corresponding parse graphs (pg's) of the AOG. Our XAI model takes pg's as input and provides answers to the user's questions using the following types of reasoning: direct evidence (e.g., detection scores), part-based inference (e.g., detected parts provide evidence for the concept asked), and other evidences from spatio-temporal context (e.g., constraints from the spatio-temporal surround). We identify several correlations between user's questions and the XAI answers using Youtube Action dataset.

Closing the AI Knowledge Gap

Ziv Epstein, Blakeley H. Payne, Judy Hanwen Shen +6

AI researchers employ not only the scientific method, but also methodology from mathematics and engineering. However, the use of the scientific method - specifically hypothesis testing - in AI is typically conducted in service of engineering objectives. Growing interest in topics such as fairness and algorithmic bias show that engineering-focused questions only comprise a subset of the important questions about AI systems. This results in the AI Knowledge Gap: the number of unique AI systems grows faster than the number of studies that characterize these systems' behavior. To close this gap, we argue that the study of AI could benefit from the greater inclusion of researchers who are well positioned to formulate and test hypotheses about the behavior of AI systems. We examine the barriers preventing social and behavioral scientists from conducting such studies. Our diagnosis suggests that accelerating the scientific study of AI systems requires new incentives for academia and industry, mediated by new tools and institutions. To address these needs, we propose a two-sided marketplace called TuringBox. On one side, AI contributors upload existing and novel algorithms to be studied scientifically by others. On the other side, AI examiners develop and post machine intelligence tasks designed to evaluate and characterize algorithmic behavior. We discuss this market's potential to democratize the scientific study of AI behavior, and thus narrow the AI Knowledge Gap.

Generative AI tools are increasingly embedded in everyday work and learning, yet their fluency, opacity, and propensity to hallucinate mean that users must critically evaluate AI outputs rather than accept them at face value. The present research conceptualises critical thinking in AI use as a dispositional tendency to verify the source and content of AI-generated information, to understand how models work and where they fail, and to reflect on the broader implications of relying on AI. Across six studies (N = 1341), we developed and validated the 13-item critical thinking in AI use scale and mapped its nomological network. Study 1 generated and content-validated scale items. Study 2 supported a three-factor structure (Verification, Motivation, and Reflection). Studies 3 and 4 confirmed the higher-order model, demonstrated strong factor loadings, internal consistency, sex invariance, convergent and discriminant evidence for validity, and showed that critical thinking in AI use was positively associated with openness, extraversion, positive trait affect, and frequency of AI use. Study 5 supported the scale's test-retest reliability. Lastly, Study 6 demonstrated criterion evidence of validity for the scale, with higher critical thinking in AI use scores predicting more frequent and diverse verification strategies, greater veracity judgement accuracy in a novel and naturalistic GPT-powered AI chatbot fact-checking task, and deeper reflection about responsible AI. The current work clarifies why and how people exercise oversight over generative AI outputs and provides a validated scale and ecologically grounded paradigm to support theory testing, cross-group, and longitudinal research on critical thinking in AI use.

Foundation model developers are among the world's most important companies. As these companies become increasingly consequential, how do their transparency practices evolve? The 2025 Foundation Model Transparency Index is the third edition of an annual effort to characterize and quantify the transparency of foundation model developers. The 2025 FMTI introduces new indicators related to data acquisition, usage data, and monitoring and evaluates companies like Alibaba, DeepSeek, and xAI for the first time. The 2024 FMTI reported that transparency was improving, but the 2025 FMTI finds this progress has deteriorated: the average score out of 100 fell from 58 in 2024 to 40 in 2025. Companies are most opaque about their training data and training compute as well as the post-deployment usage and impact of their flagship models. In spite of this general trend, IBM stands out as a positive outlier, scoring 95, in contrast to the lowest scorers, xAI and Midjourney, at just 14. The five members of the Frontier Model Forum we score end up in the middle of the Index: we posit that these companies avoid reputational harms from low scores but lack incentives to be transparency leaders. As policymakers around the world increasingly mandate certain types of transparency, this work reveals the current state of transparency for foundation model developers, how it may change given newly enacted policy, and where more aggressive policy interventions are necessary to address critical information deficits.