Financial institutions and businesses face an ongoing challenge from fraudulent transactions, prompting the need for effective detection methods. Detecting credit card fraud is crucial for identifying and preventing unauthorized transactions.Timely detection of fraud enables investigators to take swift actions to mitigate further losses. However, the investigation process is often time-consuming, limiting the number of alerts that can be thoroughly examined each day. Therefore, the primary objective of a fraud detection model is to provide accurate alerts while minimizing false alarms and missed fraud cases. In this paper, we introduce a state-of-the-art hybrid ensemble (ENS) dependable Machine learning (ML) model that intelligently combines multiple algorithms with proper weighted optimization using Grid search, including Decision Tree (DT), Random Forest (RF), K-Nearest Neighbor (KNN), and Multilayer Perceptron (MLP), to enhance fraud identification. To address the data imbalance issue, we employ the Instant Hardness Threshold (IHT) technique in conjunction with Logistic Regression (LR), surpassing conventional approaches. Our experiments are conducted on a publicly available credit card dataset comprising 284,807 transactions. The proposed model achieves impressive accuracy rates of 99.66%, 99.73%, 98.56%, and 99.79%, and a perfect 100% for the DT, RF, KNN, MLP and ENS models, respectively. The hybrid ensemble model outperforms existing works, establishing a new benchmark for detecting fraudulent transactions in high-frequency scenarios. The results highlight the effectiveness and reliability of our approach, demonstrating superior performance metrics and showcasing its exceptional potential for real-world fraud detection applications.

Machine learning models trained with differentially-private (DP) algorithms such as DP-SGD enjoy resilience against a wide range of privacy attacks. Although it is possible to derive bounds for some attacks based solely on an $(\varepsilon,\delta)$-DP guarantee, meaningful bounds require a small enough privacy budget (i.e., injecting a large amount of noise), which results in a large loss in utility. This paper presents a new approach to evaluate the privacy of machine learning models against specific record-level threats, such as membership and attribute inference, without the indirection through DP. We focus on the popular DP-SGD algorithm, and derive simple closed-form bounds. Our proofs model DP-SGD as an information theoretic channel whose inputs are the secrets that an attacker wants to infer (e.g., membership of a data record) and whose outputs are the intermediate model parameters produced by iterative optimization. We obtain bounds for membership inference that match state-of-the-art techniques, whilst being orders of magnitude faster to compute. Additionally, we present a novel data-dependent bound against attribute inference. Our results provide a direct, interpretable, and practical way to evaluate the privacy of trained models against specific inference threats without sacrificing utility.

Advances in artificial intelligence (AI) have achieved expert-level performance in medical imaging applications. Notably, self-supervised vision-language foundation models can detect a broad spectrum of pathologies without relying on explicit training annotations. However, it is crucial to ensure that these AI models do not mirror or amplify human biases, thereby disadvantaging historically marginalized groups such as females or Black patients. The manifestation of such biases could systematically delay essential medical care for certain patient subgroups. In this study, we investigate the algorithmic fairness of state-of-the-art vision-language foundation models in chest X-ray diagnosis across five globally-sourced datasets. Our findings reveal that compared to board-certified radiologists, these foundation models consistently underdiagnose marginalized groups, with even higher rates seen in intersectional subgroups, such as Black female patients. Such demographic biases present over a wide range of pathologies and demographic attributes. Further analysis of the model embedding uncovers its significant encoding of demographic information. Deploying AI systems with these biases in medical imaging can intensify pre-existing care disparities, posing potential challenges to equitable healthcare access and raising ethical questions about their clinical application.

In this paper, we investigate the interplay between attention heads and specialized "next-token" neurons in the Multilayer Perceptron that predict specific tokens. By prompting an LLM like GPT-4 to explain these model internals, we can elucidate attention mechanisms that activate certain next-token neurons. Our analysis identifies attention heads that recognize contexts relevant to predicting a particular token, activating the associated neuron through the residual connection. We focus specifically on heads in earlier layers consistently activating the same next-token neuron across similar prompts. Exploring these differential activation patterns reveals that heads that specialize for distinct linguistic contexts are tied to generating certain tokens. Overall, our method combines neural explanations and probing isolated components to illuminate how attention enables context-dependent, specialized processing in LLMs.

Wireless Sensor Networks (WSNs) play a pivotal role as infrastructures, encompassing both stationary and mobile sensors. These sensors self-organize and establish multi-hop connections for communication, collectively sensing, gathering, processing, and transmitting data about their surroundings. Despite their significance, WSNs face rapid and detrimental attacks that can disrupt functionality. Existing intrusion detection methods for WSNs encounter challenges such as low detection rates, computational overhead, and false alarms. These issues stem from sensor node resource constraints, data redundancy, and high correlation within the network. To address these challenges, we propose an innovative intrusion detection approach that integrates Machine Learning (ML) techniques with the Synthetic Minority Oversampling Technique Tomek Link (SMOTE-TomekLink) algorithm. This blend synthesizes minority instances and eliminates Tomek links, resulting in a balanced dataset that significantly enhances detection accuracy in WSNs. Additionally, we incorporate feature scaling through standardization to render input features consistent and scalable, facilitating more precise training and detection. To counteract imbalanced WSN datasets, we employ the SMOTE-Tomek resampling technique, mitigating overfitting and underfitting issues. Our comprehensive evaluation, using the WSN Dataset (WSN-DS) containing 374,661 records, identifies the optimal model for intrusion detection in WSNs. The standout outcome of our research is the remarkable performance of our model. In binary, it achieves an accuracy rate of 99.78% and in multiclass, it attains an exceptional accuracy rate of 99.92%. These findings underscore the efficiency and superiority of our proposal in the context of WSN intrusion detection, showcasing its effectiveness in detecting and mitigating intrusions in WSNs.

Posidonia oceanica is a protected endemic seagrass of Mediterranean sea that fosters biodiversity, stores carbon, releases oxygen, and provides habitat to numerous sea organisms. Leveraging augmented research, we collected a comprehensive dataset of 174 features compiled from diverse data sources. Through machine learning analysis, we discovered the existence of a robust correlation between the exact location of P. oceanica and water biogeochemical properties. The model's feature importance, showed that carbon-related variables as net biomass production and downward surface mass flux of carbon dioxide have their values altered in the areas with P. oceanica, which in turn can be used for indirect location of P. oceanica meadows. The study provides the evidence of the plant's ability to exert a global impact on the environment and underscores the crucial role of this plant in sea ecosystems, emphasizing the need for its conservation and management.

The use of machine learning algorithms in healthcare can amplify social injustices and health inequities. While the exacerbation of biases can occur and compound during the problem selection, data collection, and outcome definition, this research pertains to some generalizability impediments that occur during the development and the post-deployment of machine learning classification algorithms. Using the Framingham coronary heart disease data as a case study, we show how to effectively select a probability cutoff to convert a regression model for a dichotomous variable into a classifier. We then compare the sampling distribution of the predictive performance of eight machine learning classification algorithms under four training/testing scenarios to test their generalizability and their potential to perpetuate biases. We show that both the Extreme Gradient Boosting, and Support Vector Machine are flawed when trained on an unbalanced dataset. We introduced and show that the double discriminant scoring of type I is the most generalizable as it consistently outperforms the other classification algorithms regardless of the training/testing scenario. Finally, we introduce a methodology to extract an optimal variable hierarchy for a classification algorithm, and illustrate it on the overall, male and female Framingham coronary heart disease data.

Bayesian causal inference, i.e., inferring a posterior over causal models for the use in downstream causal reasoning tasks, poses a hard computational inference problem that is little explored in literature. In this work, we combine techniques from order-based MCMC structure learning with recent advances in gradient-based graph learning into an effective Bayesian causal inference framework. Specifically, we decompose the problem of inferring the causal structure into (i) inferring a topological order over variables and (ii) inferring the parent sets for each variable. When limiting the number of parents per variable, we can exactly marginalise over the parent sets in polynomial time. We further use Gaussian processes to model the unknown causal mechanisms, which also allows their exact marginalisation. This introduces a Rao-Blackwellization scheme, where all components are eliminated from the model, except for the causal order, for which we learn a distribution via gradient-based optimisation. The combination of Rao-Blackwellization with our sequential inference procedure for causal orders yields state-of-the-art on linear and non-linear additive noise benchmarks with scale-free and Erdos-Renyi graph structures.

Collaborative Machine Learning (CML) allows participants to jointly train a machine learning model while keeping their training data private. In scenarios where privacy is a strong requirement, such as health-related applications, safety is also a primary concern. This means that privacy-preserving CML processes must produce models that output correct and reliable decisions \emph{even in the presence of potentially untrusted participants}. In response to this issue, researchers propose to use \textit{robust aggregators} that rely on metrics which help filter out malicious contributions that could compromise the training process. In this work, we formalize the landscape of robust aggregators in the literature. Our formalization allows us to show that existing robust aggregators cannot fulfill their goal: either they use distance-based metrics that cannot accurately identify targeted malicious updates; or propose methods whose success is in direct conflict with the ability of CML participants to learn from others and therefore cannot eliminate the risk of manipulation without preventing learning.

Addressing heart failure (HF) as a prevalent global health concern poses difficulties in implementing innovative approaches for enhanced patient care. Predicting mortality rates in HF patients, in particular, is difficult yet critical, necessitating individualized care, proactive management, and enabling educated decision-making to enhance outcomes. Recently, the significance of voice biomarkers coupled with Machine Learning (ML) has surged, demonstrating remarkable efficacy, particularly in predicting heart failure. The synergy of voice analysis and ML algorithms provides a non-invasive and easily accessible means to evaluate patients' health. However, there is a lack of voice biomarkers for predicting mortality rates among heart failure patients with standardized speech protocols. Here, we demonstrate a powerful and effective ML model for predicting mortality rates in hospitalized HF patients through the utilization of voice biomarkers. By seamlessly integrating voice biomarkers into routine patient monitoring, this strategy has the potential to improve patient outcomes, optimize resource allocation, and advance patient-centered HF management. In this study, a Machine Learning system, specifically a logistic regression model, is trained to predict patients' 5-year mortality rates using their speech as input. The model performs admirably and consistently, as demonstrated by cross-validation and statistical approaches (p-value < 0.001). Furthermore, integrating NT-proBNP, a diagnostic biomarker in HF, improves the model's predictive accuracy substantially.