Foundational Models (FMs) are gaining increasing attention in the biomedical AI ecosystem due to their ability to represent and contextualize multimodal biomedical data. These capabilities make FMs a valuable tool for a variety of tasks, including biomedical reasoning, hypothesis generation, and interpreting complex imaging data. In this review paper, we address the unique challenges associated with establishing an ethical and trustworthy biomedical AI ecosystem, with a particular focus on the development of FMs and their downstream applications. We explore strategies that can be implemented throughout the biomedical AI pipeline to effectively tackle these challenges, ensuring that these FMs are translated responsibly into clinical and translational settings. Additionally, we emphasize the importance of key stewardship and co-design principles that not only ensure robust regulation but also guarantee that the interests of all stakeholders, especially those involved in or affected by these clinical and translational applications are adequately represented. We aim to empower the biomedical AI community to harness these models responsibly and effectively. As we navigate this exciting frontier, our collective commitment to ethical stewardship, co-design, and responsible translation will be instrumental in ensuring that the evolution of FMs truly enhances patient care and medical decision making, ultimately leading to a more equitable and trustworthy biomedical AI ecosystem.

Web-based Large Language Model (LLM) services have been widely adopted and have become an integral part of our Internet experience. Third-party plugins enhance the functionalities of LLM by enabling access to real-world data and services. However, the privacy consequences associated with these services and their third-party plugins are not well understood. Sensitive prompt data are stored, processed, and shared by cloud-based LLM providers and third-party plugins. In this paper, we propose Casper, a prompt sanitization technique that aims to protect user privacy by detecting and removing sensitive information from user inputs before sending them to LLM services. Casper runs entirely on the user's device as a browser extension and does not require any changes to the online LLM services. At the core of Casper is a three-layered sanitization mechanism consisting of a rule-based filter, a Machine Learning (ML)-based named entity recognizer, and a browser-based local LLM topic identifier. We evaluate Casper on a dataset of 4000 synthesized prompts and show that it can effectively filter out Personal Identifiable Information (PII) and privacy-sensitive topics with high accuracy, at 98.5% and 89.9%, respectively.

Retinal fundus imaging plays an essential role in diagnosing various stages of diabetic retinopathy, where exudates are critical markers of early disease onset. Prompt detection of these exudates is pivotal for enabling optometrists to arrest or significantly decelerate the disease progression. This paper introduces a novel, lightweight convolutional neural network architecture tailored for automated exudate detection, designed to identify these markers efficiently and accurately. To address the challenge of limited training data, we have incorporated domain-specific data augmentations to enhance the model's generalizability. Furthermore, we applied a suite of regularization techniques within our custom architecture to boost diagnostic accuracy while optimizing computational efficiency. Remarkably, this streamlined model contains only 4.73 million parameters a reduction of nearly 60% compared to the standard ResNet-18 model, which has 11.69 million parameters. Despite its reduced complexity, our model achieves an impressive F1 score of 90%, demonstrating its efficacy in the early detection of diabetic retinopathy through fundus imaging.

Binary program vulnerability detection is critical for software security, yet existing deep learning approaches often rely on source code analysis, limiting their ability to detect unknown vulnerabilities. To address this, we propose VulCatch, a binary-level vulnerability detection framework. VulCatch introduces a Synergy Decompilation Module (SDM) and Kolmogorov-Arnold Networks (KAN) to transform raw binary code into pseudocode using CodeT5, preserving high-level semantics for deep analysis with tools like Ghidra and IDA. KAN further enhances feature transformation, enabling the detection of complex vulnerabilities. VulCatch employs word2vec, Inception Blocks, BiLSTM Attention, and Residual connections to achieve high detection accuracy (98.88%) and precision (97.92%), while minimizing false positives (1.56%) and false negatives (2.71%) across seven CVE datasets.

This work proposes a novel and efficient quadstream BiLSTM-Attention network, abbreviated as QSLA network, for robust automatic modulation classification (AMC) of wireless signals. The proposed model exploits multiple representations of the wireless signal as inputs to the network and the feature extraction process combines convolutional and BiLSTM layers for processing the spatial and temporal features of the signal, respectively. An attention layer is used after the BiLSTM layer to emphasize the important temporal features. The experimental results on the recent and realistic RML22 dataset demonstrate the superior performance of the proposed model with an accuracy up to around 99%. The model is compared with other benchmark models in the literature in terms of classification accuracy, computational complexity, memory usage, and training time to show the effectiveness of our proposed approach.

The appreciation and utilisation of risk and uncertainty can play a key role in helping to solve some of the many ethical issues that are posed by AI. Understanding the uncertainties can allow algorithms to make better decisions by providing interrogatable avenues to check the correctness of outputs. Allowing algorithms to deal with variability and ambiguity with their inputs means they do not need to force people into uncomfortable classifications. Provenance enables algorithms to know what they know preventing possible harms. Additionally, uncertainty about provenance highlights the trustworthiness of algorithms. It is essential to compute with what we know rather than make assumptions that may be unjustified or untenable. This paper provides a perspective on the need for the importance of risk and uncertainty in the development of ethical AI, especially in high-risk scenarios. It argues that the handling of uncertainty, especially epistemic uncertainty, is critical to ensuring that algorithms do not cause harm and are trustworthy and ensure that the decisions that they make are humane.

Multiview learning (MvL) is an advancing domain in machine learning, leveraging multiple data perspectives to enhance model performance through view-consistency and view-discrepancy. Despite numerous successful multiview-based SVM models, existing frameworks predominantly focus on the consensus principle, often overlooking the complementarity principle. Furthermore, they exhibit limited robustness against noisy, error-prone, and view-inconsistent samples, prevalent in multiview datasets. To tackle the aforementioned limitations, this paper introduces Wave-MvSVM, a novel multiview support vector machine framework leveraging the wave loss (W-loss) function, specifically designed to harness both consensus and complementarity principles. Unlike traditional approaches that often overlook the complementary information among different views, the proposed Wave-MvSVM ensures a more comprehensive and resilient learning process by integrating both principles effectively. The W-loss function, characterized by its smoothness, asymmetry, and bounded nature, is particularly effective in mitigating the adverse effects of noisy and outlier data, thereby enhancing model stability. Theoretically, the W-loss function also exhibits a crucial classification-calibrated property, further boosting its effectiveness. Wave-MvSVM employs a between-view co-regularization term to enforce view consistency and utilizes an adaptive combination weight strategy to maximize the discriminative power of each view. The optimization problem is efficiently solved using a combination of GD and the ADMM, ensuring reliable convergence to optimal solutions. Theoretical analyses, grounded in Rademacher complexity, validate the generalization capabilities of the Wave-MvSVM model. Extensive empirical evaluations across diverse datasets demonstrate the superior performance of Wave-MvSVM in comparison to existing benchmark models.

Hyperspectral sensing is a valuable tool for detecting anomalies and distinguishing between materials in a scene. Hyperspectral anomaly detection (HS-AD) helps characterize the captured scenes and separates them into anomaly and background classes. It is vital in agriculture, environment, and military applications such as RSTA (reconnaissance, surveillance, and target acquisition) missions. We previously designed an equal voting ensemble of hyperspectral unmixing and three unsupervised HS-AD algorithms. We later utilized a supervised classifier to determine the weights of a voting ensemble, creating a hybrid of heterogeneous unsupervised HS-AD algorithms with a supervised classifier in a model stacking, which improved detection accuracy. However, supervised classification methods usually fail to detect novel or unknown patterns that substantially deviate from those seen previously. In this work, we evaluate our technique and other supervised and unsupervised methods using general hyperspectral data to provide new insights.

Photovoltaics (PV) are widely used to harvest solar energy, an important form of renewable energy. Photovoltaic arrays consist of multiple solar panels constructed from solar cells. Solar cells in the field are vulnerable to various defects, and electroluminescence (EL) imaging provides effective and non-destructive diagnostics to detect those defects. We use multiple traditional machine learning and modern deep learning models to classify EL solar cell images into different functional/defective categories. Because of the asymmetry in the number of functional vs. defective cells, an imbalanced label problem arises in the EL image data. The current literature lacks insights on which methods and metrics to use for model training and prediction. In this paper, we comprehensively compare different machine learning and deep learning methods under different performance metrics on the classification of solar cell EL images from monocrystalline and polycrystalline modules. We provide a comprehensive discussion on different metrics. Our results provide insights and guidelines for practitioners in selecting prediction methods and performance metrics.

Despite the massive attention given to time-series explanations due to their extensive applications, a notable limitation in existing approaches is their primary reliance on the time-domain. This overlooks the inherent characteristic of time-series data containing both time and frequency features. In this work, we present Spectral eXplanation (SpectralX), an XAI framework that provides time-frequency explanations for time-series black-box classifiers. This easily adaptable framework enables users to "plug-in" various perturbation-based XAI methods for any pre-trained time-series classification models to assess their impact on the explanation quality without having to modify the framework architecture. Additionally, we introduce Feature Importance Approximations (FIA), a new perturbation-based XAI method. These methods consist of feature insertion, deletion, and combination techniques to enhance computational efficiency and class-specific explanations in time-series classification tasks. We conduct extensive experiments in the generated synthetic dataset and various UCR Time-Series datasets to first compare the explanation performance of FIA and other existing perturbation-based XAI methods in both time-domain and time-frequency domain, and then show the superiority of our FIA in the time-frequency domain with the SpectralX framework. Finally, we conduct a user study to confirm the practicality of our FIA in SpectralX framework for class-specific time-frequency based time-series explanations. The source code is available in https://github.com/gustmd0121/Time_is_not_Enough