Research Papers

Explainable AI has become a common term in the literature, scrutinized by computer scientists and statisticians and highlighted by psychological or philosophical researchers. One major effort many researchers tackle is constructing general guidelines for XAI schemes, which we derived from our study. While some areas of XAI are well studied, we focus on uncertainty explanations and consider global explanations, which are often left out. We chose an algorithm that covers various concepts simultaneously, such as uncertainty, robustness, and global XAI, and tested its ability to calibrate trust. We then checked whether an algorithm that aims to provide more of an intuitive visual understanding, despite being complicated to understand, can provide higher user satisfaction and human interpretability.

Traditional fair use can no longer respond to the challenges posed by generative AI. Drawing on a comparative analysis of China's Ultraman and the U.S. cases Bartz v. Anthropic and Kadrey v. Meta, this article proposes "Develop-Fair Use" (DFU). DFU treats AI fair use (AIFU) not as a fixed exception but as a dynamic tool of judicial balancing that shifts analysis from closed scenarios to an evaluative rule for open-ended contexts. The judicial focus moves from formal classification of facts to a substantive balancing of competition in relevant markets. Although China and the U.S. follow different paths, both reveal this logic: Ultraman, by articulating a "four-context analysis," creates institutional space for AI industry development; the debate over the fourth factor, market impact, in the two U.S. cases, especially Kadrey's "market dilution" claim, expands review from substitution in copyright markets to wider industrial competition. The core of DFU is to recognize and balance the tension in relevant markets between an emerging AI industry that invokes fair use to build its markets and a publishing industry that develops markets, including one for "training licenses," to resist fair use. The boundary of fair use is therefore not a product of pure legal deduction but a case-specific factual judgment grounded in evolving market realities. This approach aims both to trim excess copyright scope and to remedy shortfalls in market competition.

Deep learning offers a promising avenue for automating many recognition tasks in fields such as medicine and forensics. However, the black-box nature of these models hinders their adoption in high-stakes applications where trust and accountability are required. For 3D shape recognition tasks in particular, this paper introduces the Class Node Graph Attention Network (CGAT) architecture to address this need. Applied to 3D meshes of third molars derived from CBCT images, for Demirjian stage allocation, CGAT utilizes graph attention convolutions and an inherent attention mechanism, visualized via attention rollout, to explain its decision-making process. We evaluated the local mean curvature and distance to centroid node features, both individually and in combination, as well as model depth, finding that models incorporating directed edges to a global CLS node produced more intuitive attention maps, while also yielding desirable classification performance. We analyzed the attention-based explanations of the models, and their predictive performances to propose optimal settings for the CGAT. The combination of local mean curvature and distance to centroid as node features yielded a slight performance increase with 0.76 weighted F1 score, and more comprehensive attention visualizations. The CGAT architecture's ability to generate human-understandable attention maps can enhance trust and facilitate expert validation of model decisions. While demonstrated on dental data, CGAT is broadly applicable to graph-based classification and regression tasks, promoting wider adoption of transparent and competitive deep learning models in high-stakes environments.

Explainable AI (XAI) has become an increasingly important topic for understanding and attributing the predictions made by complex Time Series Classification (TSC) models. Among attribution methods, SHapley Additive exPlanations (SHAP) is widely regarded as an excellent attribution method; but its computational complexity, which scales exponentially with the number of features, limits its practicality for long time series. To address this, recent studies have shown that aggregating features via segmentation, to compute a single attribution value for a group of consecutive time points, drastically reduces SHAP running time. However, the choice of the optimal segmentation strategy remains an open question. In this work, we investigated eight different Time Series Segmentation algorithms to understand how segment compositions affect the explanation quality. We evaluate these approaches using two established XAI evaluation methodologies: InterpretTime and AUC Difference. Through experiments on both Multivariate (MTS) and Univariate Time Series (UTS), we find that the number of segments has a greater impact on explanation quality than the specific segmentation method. Notably, equal-length segmentation consistently outperforms most of the custom time series segmentation algorithms. Furthermore, we introduce a novel attribution normalisation technique that weights segments by their length and we show that it consistently improves attribution quality.

Many AI alignment discussions of "runaway optimisation" focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective (e.g., "paperclip maximiser", specification gaming) at the expense of everything else. LLM-based systems are often assumed to be safer because they function as next-token predictors rather than persistent optimisers. We empirically test this assumption by placing LLMs in simple, long-horizon control-style environments that require maintaining state of or balancing objectives over time: single- and multi-objective homeostasis, balancing unbounded objectives with diminishing returns, and sustainability of a renewable resource. We find that, although LLMs frequently behave appropriately for many steps and clearly understand the stated objectives, they often lose context in structured ways and drift into runaway behaviours: ignoring homeostatic targets, collapsing from multi-objective trade-offs into single-objective maximisation - thus failing to respect concave utility structures. These failures emerge reliably after initial periods of competent behaviour and exhibit characteristic patterns (including self-imitative oscillations, unbounded maximisation, and reverting to single-objective optimisation), even though the context window is far from full at that point. The problem is not that the LLMs just lose context and become incoherent. Although LLMs appear multi-objective and bounded on the surface, their behaviour under sustained interaction involving multiple objectives, is systematically biased towards acting like single-objective, unbounded, poorly aligned optimisers. We hypothesise a token-level pattern reinforcement attractor: LLMs may increasingly derive actions from the token patterns of their recent action history rather than from the original instructions. Why this happens only in multi-objective settings remains an open question.

Artificial intelligence (AI) is increasingly used in the automotive industry for applications such as driving style classification, which aims to improve road safety, efficiency, and personalize user experiences. While deep learning (DL) models, such as Long Short-Term Memory (LSTM) networks, excel at this task, their black-box nature limits interpretability and trust. This paper proposes a machine learning (ML)-based method that balances high accuracy with interpretability. We introduce a high-quality dataset, CARLA-Drive, and leverage ML techniques like Random Forest (RF), Gradient Boosting (XGBoost), and Support Vector Machine (SVM), which are efficient, lightweight, and interpretable. In addition, we apply the SHAP (Shapley Additive Explanations) explainability technique to provide personalized recommendations for safer driving. Achieving an accuracy of 0.92 on a three-class classification task with both RF and XGBoost classifiers, our approach matches DL models in performance while offering transparency and practicality for real-world deployment in intelligent transportation systems.

Auditability is defined as the capacity of AI systems to be independently assessed for compliance with ethical, legal, and technical standards throughout their lifecycle. The chapter explores how auditability is being formalized through emerging regulatory frameworks, such as the EU AI Act, which mandate documentation, risk assessments, and governance structures. It analyzes the diverse challenges facing AI auditability, including technical opacity, inconsistent documentation practices, lack of standardized audit tools and metrics, and conflicting principles within existing responsible AI frameworks. The discussion highlights the need for clear guidelines, harmonized international regulations, and robust socio-technical methodologies to operationalize auditability at scale. The chapter concludes by emphasizing the importance of multi-stakeholder collaboration and auditor empowerment in building an effective AI audit ecosystem. It argues that auditability must be embedded in AI development practices and governance infrastructures to ensure that AI systems are not only functional but also ethically and legally aligned.

This paper presents an artistic and technical investigation into the attention mechanisms of video diffusion transformers. Inspired by early video artists who manipulated analog video signals to create new visual aesthetics, this study proposes a method for extracting and visualizing cross-attention maps in generative video models. Built on the open-source Wan model, our tool provides an interpretable window into the temporal and spatial behavior of attention in text-to-video generation. Through exploratory probes and an artistic case study, we examine the potential of attention maps as both analytical tools and raw artistic material. This work contributes to the growing field of Explainable AI for the Arts (XAIxArts), inviting artists to reclaim the inner workings of AI as a creative medium.

Khiops: An End-to-End, Frugal AutoML and XAI Machine Learning Solution for Large, Multi-Table Databases

Marc Boullé, Nicolas Voisine, Bruno Guerraz +10

Khiops is an open source machine learning tool designed for mining large multi-table databases. Khiops is based on a unique Bayesian approach that has attracted academic interest with more than 20 publications on topics such as variable selection, classification, decision trees and co-clustering. It provides a predictive measure of variable importance using discretisation models for numerical data and value clustering for categorical data. The proposed classification/regression model is a naive Bayesian classifier incorporating variable selection and weight learning. In the case of multi-table databases, it provides propositionalisation by automatically constructing aggregates. Khiops is adapted to the analysis of large databases with millions of individuals, tens of thousands of variables and hundreds of millions of records in secondary tables. It is available on many environments, both from a Python library and via a user interface.

Private, Verifiable, and Auditable AI Systems

Tobin South

The growing societal reliance on artificial intelligence necessitates robust frameworks for ensuring its security, accountability, and trustworthiness. This thesis addresses the complex interplay between privacy, verifiability, and auditability in modern AI, particularly in foundation models. It argues that technical solutions that integrate these elements are critical for responsible AI innovation. Drawing from international policy contributions and technical research to identify key risks in the AI pipeline, this work introduces novel technical solutions for critical privacy and verifiability challenges. Specifically, the research introduces techniques for enabling verifiable and auditable claims about AI systems using zero-knowledge cryptography; utilizing secure multi-party computation and trusted execution environments for auditable, confidential deployment of large language models and information retrieval; and implementing enhanced delegation mechanisms, credentialing systems, and access controls to secure interactions with autonomous and multi-agent AI systems. Synthesizing these technical advancements, this dissertation presents a cohesive perspective on balancing privacy, verifiability, and auditability in foundation model-based AI systems, offering practical blueprints for system designers and informing policy discussions on AI safety and governance.

Rice is a staple food of global importance in terms of trade, nutrition, and economic growth. Among Asian nations such as China, India, Pakistan, Thailand, Vietnam and Indonesia are leading producers of both long and short grain varieties, including basmati, jasmine, arborio, ipsala, and kainat saila. To ensure consumer satisfaction and strengthen national reputations, monitoring rice crops and grain quality is essential. Manual inspection, however, is labour intensive, time consuming and error prone, highlighting the need for automated solutions for quality control and yield improvement. This study proposes an automated approach to classify five rice grain varieties using Convolutional Neural Networks (CNN). A publicly available dataset of 75000 images was used for training and testing. Model evaluation employed accuracy, recall, precision, F1-score, ROC curves, and confusion matrices. Results demonstrated high classification accuracy with minimal misclassifications, confirming the model effectiveness in distinguishing rice varieties. In addition, an accurate diagnostic method for rice leaf diseases such as Brown Spot, Blast, Bacterial Blight, and Tungro was developed. The framework combined explainable artificial intelligence (XAI) with deep learning models including CNN, VGG16, ResNet50, and MobileNetV2. Explainability techniques such as SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) revealed how specific grain and leaf features influenced predictions, enhancing model transparency and reliability. The findings demonstrate the strong potential of deep learning in agricultural applications, paving the way for robust, interpretable systems that can support automated crop quality inspection and disease diagnosis, ultimately benefiting farmers, consumers, and the agricultural economy.

Conversational AI and Large Language Models (LLMs) have become powerful tools across domains, including cybersecurity, where they help detect threats early and improve response times. However, challenges such as false positives and complex model management still limit trust. Although Explainable AI (XAI) aims to make AI decisions more transparent, many security analysts remain uncertain about its usefulness. This study presents a framework that detects anomalies and provides high-quality explanations through visual tools BERTViz and Captum, combined with natural language reports based on attention outputs. This reduces manual effort and speeds up remediation. Our comparative analysis showed that RoBERTa offers high accuracy (99.6 %) and strong anomaly detection, outperforming Falcon-7B and DeBERTa, as well as exhibiting better flexibility than large-scale Mistral-7B on the HDFS dataset from LogHub. User feedback confirms the chatbot's ease of use and improved understanding of anomalies, demonstrating the ability of the developed framework to strengthen cybersecurity workflows.