Research Papers

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.

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.

The joint implementation of federated learning (FL) and explainable artificial intelligence (XAI) could allow training models from distributed data and explaining their inner workings while preserving essential aspects of privacy. Toward establishing the benefits and tensions associated with their interplay, this scoping review maps the publications that jointly deal with FL and XAI, focusing on publications that reported an interplay between FL and model interpretability or post-hoc explanations. Out of the 37 studies meeting our criteria, only one explicitly and quantitatively analyzed the influence of FL on model explanations, revealing a significant research gap. The aggregation of interpretability metrics across FL nodes created generalized global insights at the expense of node-specific patterns being diluted. Several studies proposed FL algorithms incorporating explanation methods to safeguard the learning process against defaulting or malicious nodes. Studies using established FL libraries or following reporting guidelines are a minority. More quantitative research and structured, transparent practices are needed to fully understand their mutual impact and under which conditions it happens.

Federated Learning (FL) has become a key method for preserving data privacy in Internet of Things (IoT) environments, as it trains Machine Learning (ML) models locally while transmitting only model updates. Despite this design, FL remains susceptible to threats such as model inversion and membership inference attacks, which can reveal private training data. Differential Privacy (DP) techniques are often introduced to mitigate these risks, but simply injecting DP noise into black-box ML models can compromise accuracy, particularly in dynamic IoT contexts, where continuous, lifelong learning leads to excessive noise accumulation. To address this challenge, we propose Federated HyperDimensional computing with Privacy-preserving (FedHDPrivacy), an eXplainable Artificial Intelligence (XAI) framework that integrates neuro-symbolic computing and DP. Unlike conventional approaches, FedHDPrivacy actively monitors the cumulative noise across learning rounds and adds only the additional noise required to satisfy privacy constraints. In a real-world application for monitoring manufacturing machining processes, FedHDPrivacy maintains high performance while surpassing standard FL frameworks - Federated Averaging (FedAvg), Federated Proximal (FedProx), Federated Normalized Averaging (FedNova), and Federated Optimization (FedOpt) - by up to 37%. Looking ahead, FedHDPrivacy offers a promising avenue for further enhancements, such as incorporating multimodal data fusion.

WalledEval is a comprehensive AI safety testing toolkit designed to evaluate large language models (LLMs). It accommodates a diverse range of models, including both open-weight and API-based ones, and features over 35 safety benchmarks covering areas such as multilingual safety, exaggerated safety, and prompt injections. The framework supports both LLM and judge benchmarking and incorporates custom mutators to test safety against various text-style mutations, such as future tense and paraphrasing. Additionally, WalledEval introduces WalledGuard, a new, small, and performant content moderation tool, and two datasets: SGXSTest and HIXSTest, which serve as benchmarks for assessing the exaggerated safety of LLMs and judges in cultural contexts. We make WalledEval publicly available at https://github.com/walledai/walledeval.

Ethical Framework for Responsible Foundational Models in Medical Imaging

Debesh Jha, Gorkem Durak, Abhijit Das +33

The emergence of foundational models represents a paradigm shift in medical imaging, offering extraordinary capabilities in disease detection, diagnosis, and treatment planning. These large-scale artificial intelligence systems, trained on extensive multimodal and multi-center datasets, demonstrate remarkable versatility across diverse medical applications. However, their integration into clinical practice presents complex ethical challenges that extend beyond technical performance metrics. This study examines the critical ethical considerations at the intersection of healthcare and artificial intelligence. Patient data privacy remains a fundamental concern, particularly given these models' requirement for extensive training data and their potential to inadvertently memorize sensitive information. Algorithmic bias poses a significant challenge in healthcare, as historical disparities in medical data collection may perpetuate or exacerbate existing healthcare inequities across demographic groups. The complexity of foundational models presents significant challenges regarding transparency and explainability in medical decision-making. We propose a comprehensive ethical framework that addresses these challenges while promoting responsible innovation. This framework emphasizes robust privacy safeguards, systematic bias detection and mitigation strategies, and mechanisms for maintaining meaningful human oversight. By establishing clear guidelines for development and deployment, we aim to harness the transformative potential of foundational models while preserving the fundamental principles of medical ethics and patient-centered care.

In the dynamic and ever-changing domain of Unmanned Aerial Vehicles (UAVs), the utmost importance lies in guaranteeing resilient and lucid security measures. This study highlights the necessity of implementing a Zero Trust Architecture (ZTA) to enhance the security of unmanned aerial vehicles (UAVs), hence departing from conventional perimeter defences that may expose vulnerabilities. The Zero Trust Architecture (ZTA) paradigm requires a rigorous and continuous process of authenticating all network entities and communications. The accuracy of our methodology in detecting and identifying unmanned aerial vehicles (UAVs) is 84.59\%. This is achieved by utilizing Radio Frequency (RF) signals within a Deep Learning framework, a unique method. Precise identification is crucial in Zero Trust Architecture (ZTA), as it determines network access. In addition, the use of eXplainable Artificial Intelligence (XAI) tools such as SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) contributes to the improvement of the model's transparency and interpretability. Adherence to Zero Trust Architecture (ZTA) standards guarantees that the classifications of unmanned aerial vehicles (UAVs) are verifiable and comprehensible, enhancing security within the UAV field.

Generative AI, exemplified by models like transformers, has opened up new possibilities in various domains but also raised concerns about fairness, transparency and reliability, especially in fields like medicine and law. This paper emphasizes the urgency of ensuring fairness and quality in these domains through generative AI. It explores using cryptographic techniques, particularly Zero-Knowledge Proofs (ZKPs), to address concerns regarding performance fairness and accuracy while protecting model privacy. Applying ZKPs to Machine Learning models, known as ZKML (Zero-Knowledge Machine Learning), enables independent validation of AI-generated content without revealing sensitive model information, promoting transparency and trust. ZKML enhances AI fairness by providing cryptographic audit trails for model predictions and ensuring uniform performance across users. We introduce snarkGPT, a practical ZKML implementation for transformers, to empower users to verify output accuracy and quality while preserving model privacy. We present a series of empirical results studying snarkGPT's scalability and performance to assess the feasibility and challenges of adopting a ZKML-powered approach to capture quality and performance fairness problems in generative AI models.

AI Ethics on Blockchain: Topic Analysis on Twitter Data for Blockchain Security

Yihang Fu, Zesen Zhuang, Luyao Zhang

Blockchain has empowered computer systems to be more secure using a distributed network. However, the current blockchain design suffers from fairness issues in transaction ordering. Miners are able to reorder transactions to generate profits, the so-called miner extractable value (MEV). Existing research recognizes MEV as a severe security issue and proposes potential solutions, including prominent Flashbots. However, previous studies have mostly analyzed blockchain data, which might not capture the impacts of MEV in a much broader AI society. Thus, in this research, we applied natural language processing (NLP) methods to comprehensively analyze topics in tweets on MEV. We collected more than 20000 tweets with #MEV and #Flashbots hashtags and analyzed their topics. Our results show that the tweets discussed profound topics of ethical concern, including security, equity, emotional sentiments, and the desire for solutions to MEV. We also identify the co-movements of MEV activities on blockchain and social media platforms. Our study contributes to the literature at the interface of blockchain security, MEV solutions, and AI ethics.

Foiling Explanations in Deep Neural Networks

Snir Vitrack Tamam, Raz Lapid, Moshe Sipper

Deep neural networks (DNNs) have greatly impacted numerous fields over the past decade. Yet despite exhibiting superb performance over many problems, their black-box nature still poses a significant challenge with respect to explainability. Indeed, explainable artificial intelligence (XAI) is crucial in several fields, wherein the answer alone -- sans a reasoning of how said answer was derived -- is of little value. This paper uncovers a troubling property of explanation methods for image-based DNNs: by making small visual changes to the input image -- hardly influencing the network's output -- we demonstrate how explanations may be arbitrarily manipulated through the use of evolution strategies. Our novel algorithm, AttaXAI, a model-agnostic, adversarial attack on XAI algorithms, only requires access to the output logits of a classifier and to the explanation map; these weak assumptions render our approach highly useful where real-world models and data are concerned. We compare our method's performance on two benchmark datasets -- CIFAR100 and ImageNet -- using four different pretrained deep-learning models: VGG16-CIFAR100, VGG16-ImageNet, MobileNet-CIFAR100, and Inception-v3-ImageNet. We find that the XAI methods can be manipulated without the use of gradients or other model internals. Our novel algorithm is successfully able to manipulate an image in a manner imperceptible to the human eye, such that the XAI method outputs a specific explanation map. To our knowledge, this is the first such method in a black-box setting, and we believe it has significant value where explainability is desired, required, or legally mandatory.

The study of representation universality in AI models reveals growing convergence across domains, modalities, and architectures. However, the practical applications of representation universality remain largely unexplored. We bridge this gap by demonstrating that safety interventions can be transferred between models through learned mappings of their shared activation spaces. We demonstrate this approach on two well-established AI safety tasks: backdoor removal and refusal of harmful prompts, showing successful transfer of steering vectors that alter the models' outputs in a predictable way. Additionally, we propose a new task, \textit{corrupted capabilities}, where models are fine-tuned to embed knowledge tied to a backdoor. This tests their ability to separate useful skills from backdoors, reflecting real-world challenges. Extensive experiments across Llama, Qwen and Gemma model families show that our method enables using smaller models to efficiently align larger ones. Furthermore, we demonstrate that autoencoder mappings between base and fine-tuned models can serve as reliable ``lightweight safety switches", allowing dynamic toggling between model behaviors.

Generative artificial intelligence is increasingly transforming education by enabling adaptive learning environments, personalized instructional support, and collaborative knowledge creation, while also assisting research, assessment, and academic administration. In the context of fifth generation education systems, the integration of generative artificial intelligence offers new opportunities to enhance student engagement, support innovative pedagogical practices, and improve scholarly productivity. This study presents a systematic review of recent research on the adoption of generative artificial intelligence in primary, secondary, and higher education institutions, using established guidelines for systematic literature reviews and bibliometric analysis. The review examines applications of generative artificial intelligence for learners, educators, and researchers, and identifies key challenges including academic integrity risks, algorithmic bias, ethical concerns, data privacy issues, and unequal access to advanced educational technologies. By analyzing research trends, thematic relationships, and existing gaps, this study provides insights for the design of adaptive learning systems, the promotion of responsible use of artificial intelligence in education, and the direction of future research efforts. Overall, the findings highlight the potential of generative artificial intelligence to support human machine collaboration, lifelong learning, and inclusive educational environments, offering practical guidance for policymakers, educators, and engineers seeking to apply artificial intelligence for meaningful educational impact.