diff --git a/Final Papers/cai24.pdf b/Final Papers/cai24.pdf new file mode 100644 index 0000000..8c095e2 Binary files /dev/null and b/Final Papers/cai24.pdf differ diff --git a/Final Papers/chai24.pdf b/Final Papers/chai24.pdf new file mode 100644 index 0000000..f889ac5 Binary files /dev/null and b/Final Papers/chai24.pdf differ diff --git a/Final Papers/ehnemark24.pdf b/Final Papers/ehnemark24.pdf new file mode 100644 index 0000000..69c00fa Binary files /dev/null and b/Final Papers/ehnemark24.pdf differ diff --git a/Final Papers/hoang24.pdf b/Final Papers/hoang24.pdf new file mode 100644 index 0000000..9bab28f Binary files /dev/null and b/Final Papers/hoang24.pdf differ diff --git a/Final Papers/le24.pdf b/Final Papers/le24.pdf new file mode 100644 index 0000000..a1590e1 Binary files /dev/null and b/Final Papers/le24.pdf differ diff --git a/Final Papers/naeem24.pdf b/Final Papers/naeem24.pdf new file mode 100644 index 0000000..bfe7155 Binary files /dev/null and b/Final Papers/naeem24.pdf differ diff --git a/Final Papers/nguyen24.pdf b/Final Papers/nguyen24.pdf new file mode 100644 index 0000000..126f5ab Binary files /dev/null and b/Final Papers/nguyen24.pdf differ diff --git a/Final Papers/nguyen25.pdf b/Final Papers/nguyen25.pdf new file mode 100644 index 0000000..4eec71b Binary files /dev/null and b/Final Papers/nguyen25.pdf differ diff --git a/Final Papers/phan25.pdf b/Final Papers/phan25.pdf new file mode 100644 index 0000000..6836588 Binary files /dev/null and b/Final Papers/phan25.pdf differ diff --git a/Final Papers/salim25.pdf b/Final Papers/salim25.pdf new file mode 100644 index 0000000..e1f2212 Binary files /dev/null and b/Final Papers/salim25.pdf differ diff --git a/Final Papers/varshney24.pdf b/Final Papers/varshney24.pdf new file mode 100644 index 0000000..288c25c Binary files /dev/null and b/Final Papers/varshney24.pdf differ diff --git a/reliableai25.bib b/reliableai25.bib new file mode 100644 index 0000000..d1d4fe9 --- /dev/null +++ b/reliableai25.bib @@ -0,0 +1,201 @@ +@Proceedings{Reliable-and-Trustworthy-AI-2025, + booktitle = {Reliable and Trustworthy Artificial Intelligence 2025}, + name = {Reliable and Trustworthy Artificial Intelligence}, + shortname = {Reliable & Trustworthy AI}, + year = {2025}, + editor = {Nguyen, Hoang D. and Le, Duc-Trong and Bj{\"o}rklund, Johanna and Vu, Xuan-Son}, + volume = {310}, + start = {2025-12-12}, + end = {2025-12-12}, + conference_url = {https://workshop2025.reliable-ai.org/} +} + +@InProceedings{preface, + author = {Nguyen, Hoang D. and Le, Duc-Trong and Bj{\"o}rklund, Johanna and Vu, Xuan-Son}, + title = {Preface}, + pages = {v-vi}, + abstract = {Preface} +} + +@InProceedings{cai24, + title = {Reinforcement Learning in Online Advertising: Challenges, Prospects, and Trust}, + author = {Cai, Jingwen and Bj{\"o}rklund, Johanna}, + pages = {1-10}, + abstract = {The central decision-making processes involved in online advertising are often supported +by Reinforcement Learning (RL), which serves to optimise long-term accumulative re- +wards through interactions with evolving environments. While RL’s potential in various +real-world applications has been reviewed in extant survey works, the specific ways RL +algorithms address online advertising challenges remain unchartered. Therefore, this paper +reviews RL applications in this practice area, identifying core challenges and key issues +including trust concerns. We categorize reviewed work based on problem domains and +propose potential directions for future research. Our goal is to bridge the cross-disciplinary +gap in this field, offering perspectives and guidance for researchers and practitioners.} +} + +@InProceedings{chai24, + title = {AIQTrees: A Drone Imagery Dataset for Tree Segmentation}, + author = {Chai, Joseph and To, Alex and O' Sullivan, Barry and Nguyen, Hoang D.}, + pages = {11-18}, + abstract = {The reliability of AI models typically depends on the data they are trained with, and +accurate interpretations require large amounts of data. The scarcity of publicly available +datasets is typically encountered for specific small-scale sustainability projects, making +data accessibility a limiting factor for developing AI models for semantic segmentation +tasks. In sustainability and forestry applications, the usage of UAVs is common due to +their lightweight nature and the ability to provide a huge variety of data. In this paper, +we present a new dataset of realistic and high-quality drone images taken around sites in +Ireland. The images encompass temporal, spatial, and seasonal dimensions, which could +alter the tree appearance or illumination conditions of the images and have to be taken into +consideration. We also included a baseline benchmark for the semantic segmentation task +along with the dataset. It can be accessed at: https://github.com/ReML-AI/AIQTrees.} +} + +@InProceedings{ehnemark24, + title = {Bridging Human Cognition and AI: Enhancing Transparency and Explainability with Hierarchical Conceptual Graphs and the Knowing Protocol}, + author = {Ehnemark, Klas}, + pages = {19-23}, + abstract = {The rapid deployment of large language models (LLMs) in critical domains demands greater +transparency and explainability to build user trust and enable effective collaboration. Cur- +rent AI-human interactions largely rely on unstructured text, often resulting in misunder- +standings and limited insight into AI reasoning. We introduce a Hierarchical Conceptual +Graph Model and the Knowing Communication Protocol to bridge the gap between sym- +bolic human reasoning and sub-symbolic AI processing. Our model combines conceptual +spaces, ontologies, and hierarchical structures to explicitly represent complex knowledge, +while the Knowing Protocol, through the Knowing Markup Language (KML), facilitates +structured, machine-readable interactions. This approach enhances transparency by align- +ing AI-generated content with human cognitive structures, promoting clarity and collabo- +rative knowledge building—ultimately addressing the limitations of traditional text-based +AI tools and advancing trustworthy, explainable AI.} +} + +@InProceedings{hoang24, + title = {A lightweight and reliable framework toward real-time student engagement predictions in learning analytics}, + author = {Hoang, Long and Shorten, George and O'Sullivan, Barry and Nguyen, Hoang D.}, + pages = {24-33}, + abstract = {Learning analytics can enable the provision of meaningful feedback based on the collected data, help +educators to make decisions with and about learners, and improve learner performance. Student engagement +predictions are a key factor in generating feedback for real-time learning analytics applications, such as +dashboards. However, most previous work has been based on a heavy deep learning model, which results in +challenges for deployment in real-time applications (a resource efficiency requirement in reliable AI). This paper +proposes a lightweight deep-learning framework for predicting student engagement in video to address this +limitation. The proposed method uses customized MobileNetV2 as the backbone, with an input size of 32 by 32 +by 3, to extract features from consecutive video frames. Multi-Scale attention – Residual (MUSER) is used to +capture global information and contextual representation of the extracted features. Finally, LSTM examines the +temporal variations in video frames and yields the prediction result. We use the DAISEE dataset, the most popular +dataset in the learning analytics community, to evaluate the proposed framework. Experimental results +demonstrate that the proposed method achieves good accuracy while significantly reducing the model size +compared to other approaches.} +} + +@InProceedings{le24, + title = {Trustworthiness in Multi-Agent UAV Systems: A Scoping Review}, + author = {Le, Mai and Minghim, Rosane and O'Sullivan, Barry and Nguyen, Hoang D.}, + pages = {34-44}, + abstract = {The integration of artificial intelligence (AI) into multi-unmanned aerial vehicle-assisted +communication plays a pivotal role in sixth-generation wireless communication and be- +yond. Most AI techniques have primarily focused on AI-based applications and technical +problems, rather than examining the accountability and trustworthiness of AI models, a +crucial evaluation criteria for AI human beings. This work aims to provide a scoping re- +view of the trustworthiness of AI in multi-agent UAV systems. Firstly, we present the +background of multi-agent systems and methods to evaluate, enhance the trustworthiness +of AI systems. Secondly, we review innovative techniques that address trustworthy require- +ments in terms of safety, robustness, privacy, accountability, explainability, and fairness, +along with challenges in multi-agent UAV communications. Finally, we highlight several +promising solutions and future research directions.} +} + +@InProceedings{naeem24, + title = {Comparing Genetic Algorithms and Principal Component Analysis in Reducing Feature Dimensionality}, + author = {Naeem, Aiman and Khan, Muhammad Farhan and Rezaei, Saeid and Iqbal, Adeel and Sohail, Muhammad and Jatoi, Munsif and Shakeel, Atif}, + pages = {45-58}, + abstract = {It is important to do dimensionality reduction or feature selection so that machine learning +models can be built in an efficient and interpretable way, especially with high-dimensional +datasets. Using data up to October 2023, this study compares two methods, namely, Ge- +netic Algorithm (GA) and Principal Component Analysis (PCA), to assess their usefulness +for dimensionality reduction while preserving predictive performance. As a case study, we +applied the feature selection methodology on the Breast Cancer Wisconsin (Diagnostic) +dataset, comprised of 30 real-valued features that describe the characteristics of cell nuclei. +PCA used to reduce dimensional space of dataset by explaining 95% of variance and GA +is used to make a minimal subset of subset of relevant features based on fitness function. +To evaluate the effect of the reduced dimensionality on classification accuracy, a Random +Forest classifier was used. Experimental results shown that GA selected features provide +accuracy from the GA by 98.25% and PCA accuracy from the PCA with 93.86% which +at the cost of high computational cost. Finally, visualizations illustrated the variance re- +tained by PCA, how features provided importance in model performance using GA, and +how both influence the models. The quantitative results of this study can be used to iden- +tify the trade-off between the statistical approaches and heuristic approaches showing what +needs to be prioritized in terms of application specificity when searching for dimensionality +reduction methods.} +} + +@InProceedings{nguyen24, + title = {Reliable Cultural Knowledge Preservation in Multilingual LLMs through Model Merging}, + author = {Nguyen, Hoang Quan and Pham, Nhut Huy and Pahani, Maziyar and Bj{\"o}rklund, Johanna and Vu, Xuan-Son}, + pages = {59-66}, + abstract = {We introduce a reliable approach for enhancing multilingual language models that preserves cultural knowledge while +improving reasoning capabilities, focusing on low-resource languages. Using Qwen as a base model, we demonstrate that trust-aware model merging +can verifiably improve performance without compromising cultural understanding. Our proposed approach achieves quantifiable improvements in both +reasoning tasks and cultural benchmarks while maintaining computational efficiency. Results on Vietnamese and Arabic language tasks show consistent +performance gains while preserving cultural knowledge, offering a reliable path for developing trustworthy multilingual AI systems. Our models are +available at github.com/WARA-ML/waraml-mini-brains.} +} + +@InProceedings{varshney24, + title = {Recurrence Analysis of Integrally Private Support Vector Machine}, + author = {Varshney, Ayush K. and Torra, Vicen{\c c}}, + pages = {67-72}, + abstract = {Integral privacy, an alternative to k-Anonymity and differential privacy, focuses on creating ambiguity +for intruders by considering models generated from diverse datasets as privacy-preserving. Integral privacy calls such models +as recurring models. While prior research has primarily explored recurrence in deep learning models which have large parameter +space, this paper addresses the recurrence analysis of a typical machine learning model with relatively small parameter space like +Support Vector Machine (SVM). Models having small parameter space can have significant impact due to the presence and absence of +a datapoint. Due to this reason, one may intuitively consider that their probability to recur is low. We challenge this hypothesis +with the recurrence analysis of SVM models trained with mean samplers like stochastic gradient descent. We find that under constrained +environment SVM models recurs with high probability. This research enhances our understanding of privacy-preserving models in the context +of SVMs, providing valuable insights into their privacy guarantees.} +} + +@InProceedings{nguyen25, + title = {Reliable-Data-Split (RDS): Maximizing Model Potential with Reinforced Selection Strategy}, + author = {Nguyen, Hoang D. and Vu, Xuan-Son and Truong, Quoc-Tuan and Le, Duc-Trong}, + pages = {73-89}, + abstract = {The nexus between data characteristics and parametric models is fundamental for developing effective and +reliable artificial intelligence (AI) systems. Mismatches in data properties for model development may lead to deleterious +effects on AI model performance in machine learning practice. This paper proposes a Reliable Data Split (RDS) procedure +to learn how to select data points that will generalise the target domain adequately by employing prior knowledge of the data +generative process. We introduce a reinforced selection strategy using deep reinforcement learning with diverse black box predictors in +maximising ensemble rewards as the proxy of model performance potential while maintaining an appropriate proportionate allocation and the +independent and identically distributed (i.i.d.) assumption. A comprehensive evaluation of the RDS procedure is conducted on four real-world datasets, +including Madelon, Drug Reviews, MNIST, and Kalapa Credit Scoring Challenge, with coverage of machine learning tasks such as binary classification, +multi-class classification, and regression on multivariate, textual, and visual data. The experimental results evidently demonstrate consistent +performance improvements of trainable data samples over classical or prior data selection. Hence, we advocate the use of RDS for data splitting in the +early stage of machine learning tasks for parameter tuning, model selection and overfitting prevention, as well as, sampling in large-scale AI competitions for +searching the best possible and shift-stable solutions.} +} + +@InProceedings{phan25, + title = {Improving Continual Learning Robustness in Medical Imaging via Illumination Adaptive Transformer}, + author = {Phan, Thanh-Ngoc and Pham, Quynh-Trang Thi and Le, Duc-Trong}, + pages = {90-101}, + abstract = {Continual learning (CL) refers to the capability of a model to learn progressively from an evolving stream of data, retaining previously +acquired knowledge while integrating new information. This capability is pivotal in advancing medical image classification, especially when data availability +fluctuates. Beyond investigating CL performance under standard clean-data conditions, this paper systematically evaluates the robustness of representative +CL strategies in uncertain imaging contexts, where visual quality is degraded by varying degrees of low-light conditions and over- or under exposure. In this paper, we augment +the training and evaluation data with controlled, simulated low-light and contrast perturbations to model these uncertain conditions, which mimic real-world variability frequently +encountered in clinical acquisition environments. Our method integrates an automatic illumination calibration module, termed the Illumination Adaptive Transformer (IAT), within +existing CL frameworks to mitigate the adverse effects of such degradations. This module dynamically adjusts the image illumination and contrast, aiming to enhance the visibility +of critical features in a data-driven, end-to-end manner without requiring manual tuning or image-specific heuristics. Experiments demonstrate that incorporating the IAT module +consistently improves final classification accuracy and robustness across multiple continual learning strategies under all simulated uncertainty levels on the PathMNIST dataset.} +} + +@InProceedings{salim25, + title = {Towards a SAFETY-AI framework for Healthcare Education}, + author = {Salim, Kinza and Nana, Vanita Kouomogne and Marshall, Mark T. and Nguyen, Hoang D.}, + pages = {102-114}, + abstract = {Safety is an integral part of healthcare professionalism, and with new technological developments, such as Artificial Intelligence (AI), there is an ongoing +need to develop guardrails for healthcare education. The landscape of AI safety frameworks for healthcare education is evolving, with significant development in regulatory +compliance, ethical governance, and practical implementation approaches. This paper addresses the need for building a SAFETY-AI framework for healthcare education and proposes +a solution towards it. It also provides subjective insights regarding trustworthiness, reliability and the existing concepts of safety in healthcare setups. This work stands +as a roadmap for safety in AI practices for healthcare policy makers, educators and clinicians.} +} + +