Out-of-distribution (OOD) detection plays a key role in enhancing the robustness of artificial intelligence systems by identifying inputs that differ significantly from the training distribution, thereby preventing unreliable predictions and enabling appropriate fallback mechanisms. Developing reliable OOD detection methods is a significant challenge, and rigorous evaluation of these techniques is essential for ensuring their effectiveness, as it allows researchers to assess their performance under diverse conditions and to identify potential limitations or failure modes. Cross-validation (CV) has proven to be a highly effective tool for providing a reasonable estimate of the performance of a learning algorithm. Although OOD scenarios exhibit particular characteristics, an appropriate adaptation of CV can lead to a suitable evaluation framework for this setting. This work proposes a dual CV framework for robust evaluation of OOD detection models, aimed at improving the reliability of their assessment. The proposed evaluation framework aims to effectively integrate in-distribution (ID) and OOD data while accounting for their differing characteristics. To achieve this, ID data are partitioned using a conventional approach, whereas OOD data are divided by grouping samples based on their classes. Furthermore, we analyze the context of data with class hierarchy to propose a data splitting that considers the entire class hierarchy to obtain fair ID-OOD partitions to apply the proposed evaluation framework. This framework is called Dual Cross-Validation for Robust Out-of-Distribution Detection (DCV-ROOD). To test the validity of the evaluation framework, we selected a set of state-of-the-art OOD detection methods, both with and without outlier exposure. The results show that the method achieves very fast convergence to the true performance.

We develop a new classification framework based on the theory of coherent risk measures and systemic risk. The proposed approach is suitable for multi-class problems when the data is noisy, scarce (relative to the dimension of the problem), and the labeling might be unreliable. In the first part of our paper, we provide the foundation of the use of systemic risk models and show how to apply it in the context of linear and kernel-based multi-class problems. More advanced formulation via a system-theoretic approach with non-linear aggregation is proposed, which leads to a two-stage stochastic programming problem. A risk-averse regularized decomposition method is designed to solve the problem. We use a popular multi-class method as a benchmark in the performance analysis of the proposed classification methods. We illustrate our ideas by proposing several generalization of that method by the use of coherent measures of risk. The viability of the proposed risk-averse methods are supported theoretically and numerically. Additionally, we demonstrate that the application of systemic risk measures facilitates enforcing fairness in classification. Analysis and experiments regarding the fairness of the proposed models are carefully conducted. For all methods, our numerical experiments demonstrate that they are robust in the presence of unreliable training data and perform better on unknown data than the methods minimizing expected classification errors. Furthermore, the performance improves when the number of classes increases.

AI audits play a critical role in AI accountability and safety. One branch of the law for which AI audits are particularly salient is anti-discrimination law. Several areas of anti-discrimination law implicate the "less discriminatory alternative" (LDA) requirement, in which a protocol (e.g., model) is defensible if no less discriminatory protocol that achieves comparable performance can be found with a reasonable amount of effort. Notably, the burden of proving an LDA exists typically falls on the claimant (the party alleging discrimination). This creates a significant hurdle in AI cases, as the claimant would seemingly need to train a less discriminatory yet high-performing model, a task requiring resources and expertise beyond most litigants. Moreover, developers often shield information about and access to their model and training data as trade secrets, making it difficult to reproduce a similar model from scratch. In this work, we present a procedure enabling claimants to determine if an LDA exists, even when they have limited compute, data, information, and model access. We focus on the setting in which fairness is given by demographic parity and performance by binary cross-entropy loss. As our main result, we provide a novel closed-form upper bound for the loss-fairness Pareto frontier (PF). We show how the claimant can use it to fit a PF in the "low-resource regime," then extrapolate the PF that applies to the (large) model being contested, all without training a single large model. The expression thus serves as a scaling law for loss-fairness PFs. To use this scaling law, the claimant would require a small subsample of the train/test data. Then, the claimant can fit the context-specific PF by training as few as 7 (small) models. We stress test our main result in simulations, finding that our scaling law holds even when the exact conditions of our theory do not.

Traditional Artificial Intelligence (AI) approaches in cybersecurity exhibit fundamental limitations: inadequate conceptual grounding leading to non-robustness against novel attacks; limited instructibility impeding analyst-guided adaptation; and misalignment with cybersecurity objectives. Neuro-Symbolic (NeSy) AI has emerged with the potential to revolutionize cybersecurity AI. However, there is no systematic understanding of this emerging approach. These hybrid systems address critical cybersecurity challenges by combining neural pattern recognition with symbolic reasoning, enabling enhanced threat understanding while introducing concerning autonomous offensive capabilities that reshape threat landscapes. In this survey, we systematically characterize this field by analyzing 127 publications spanning 2019-July 2025. We introduce a Grounding-Instructibility-Alignment (G-I-A) framework to evaluate these systems, focusing on both cyber defense and cyber offense across network security, malware analysis, and cyber operations. Our analysis shows advantages of multi-agent NeSy architectures and identifies critical implementation challenges including standardization gaps, computational complexity, and human-AI collaboration requirements that constrain deployment. We show that causal reasoning integration is the most transformative advancement, enabling proactive defense beyond correlation-based approaches. Our findings highlight dual-use implications where autonomous systems demonstrate substantial capabilities in zero-day exploitation while achieving significant cost reductions, altering threat dynamics. We provide insights and future research directions, emphasizing the urgent need for community-driven standardization frameworks and responsible development practices that ensure advancement serves defensive cybersecurity objectives while maintaining societal alignment.

Robust out-of-distribution (OOD) detection is an indispensable component of modern artificial intelligence (AI) systems, especially in safety-critical applications where models must identify inputs from unfamiliar classes not seen during training. While OOD detection has been extensively studied in the machine learning literature--with both post hoc and training-based approaches--its effectiveness under noisy training labels remains underexplored. Recent studies suggest that label noise can significantly degrade OOD performance, yet principled solutions to this issue are lacking. In this work, we demonstrate that directly combining existing label noise-robust methods with OOD detection strategies is insufficient to address this critical challenge. To overcome this, we propose a robust OOD detection framework that integrates loss correction techniques from the noisy label learning literature with low-rank and sparse decomposition methods from signal processing. Extensive experiments on both synthetic and real-world datasets demonstrate that our method significantly outperforms the state-of-the-art OOD detection techniques, particularly under severe noisy label settings.

Radiology is at the center of many medical specialties, which rely on radiologists' interpretation of images from various modalities, including CT, MRI, ultrasound, and X-ray [1]. The analysis of these images is crucial for detecting and characterizing medical conditions, quantifying disease progression, and monitoring treatment efficacy across a broad spectrum of diseases. AI has the potential to enhance radiology workflows and improve radiologists' efficiency, particularly for labor-intensive tasks such as image segmentation, or specialized and/or complex tasks which are prone to inter-reader variability [2, 3]. To date, the dominant paradigm in radiological AI development has involved training specialized models for individual tasks such as segmentation, abnormality detection (e.g., tumor detection), or pathology classification. However, this "one-task, one-model" approach is exceptionally resource-intensive, as it necessitates the curation and manual annotation of large, task-specific datasets for each modality and clinical application [4, 5]. It is potentially one of the bottlenecks in moving AI radiology models into the clinical workflow. Foundation models (FM) represent a significant paradigm shift in the field of AI.

Effective Operation and Maintenance (O&M) is critical to reducing the Levelised Cost of Energy (LCOE) from wind power, yet the unstructured, free-text nature of turbine maintenance logs presents a significant barrier to automated analysis. Our paper addresses this by presenting a novel and reproducible framework for benchmarking Large Language Models (LLMs) on the task of classifying these complex industrial records. To promote transparency and encourage further research, this framework has been made publicly available as an open-source tool. We systematically evaluate a diverse suite of state-of-the-art proprietary and open-source LLMs, providing a foundational assessment of their trade-offs in reliability, operational efficiency, and model calibration. Our results quantify a clear performance hierarchy, identifying top models that exhibit high alignment with a benchmark standard and trustworthy, well-calibrated confidence scores. We also demonstrate that classification performance is highly dependent on the task's semantic ambiguity, with all models showing higher consensus on objective component identification than on interpretive maintenance actions. Given that no model achieves perfect accuracy and that calibration varies dramatically, we conclude that the most effective and responsible near-term application is a Human-in-the-Loop system, where LLMs act as a powerful assistant to accelerate and standardise data labelling for human experts, thereby enhancing O&M data quality and downstream reliability analysis.

Autonomous robots operating in dynamic environments should identify and report anomalies. Embodying proactive mitigation improves safety and operational continuity. This paper presents a multimodal anomaly detection and mitigation system that integrates vision-language models and large language models to identify and report hazardous situations and conflicts in real-time. The proposed system enables robots to perceive, interpret, report, and if possible respond to urban and environmental anomalies through proactive detection mechanisms and automated mitigation actions. A key contribution in this paper is the integration of Hazardous and Conflict states into the robot's decision-making framework, where each anomaly type can trigger specific mitigation strategies. User studies (n = 30) demonstrated the effectiveness of the system in anomaly detection with 91.2% prediction accuracy and relatively low latency response times using edge-ai architecture.

Brain tumors are serious health problems that require early diagnosis due to their high mortality rates. Diagnosing tumors by examining Magnetic Resonance Imaging (MRI) images is a process that requires expertise and is prone to error. Therefore, the need for automated diagnosis systems is increasing day by day. In this context, a robust and explainable Deep Learning (DL) model for the classification of brain tumors is proposed. In this study, a publicly available Figshare dataset containing 3,064 T1-weighted contrast-enhanced brain MRI images of three tumor types was used. First, the classification performance of nine well-known CNN architectures was evaluated to determine the most effective backbone. Among these, EfficientNetV2 demonstrated the best performance and was selected as the backbone for further development. Subsequently, an attention-based MLP-Mixer architecture was integrated into EfficientNetV2 to enhance its classification capability. The performance of the final model was comprehensively compared with basic CNNs and the methods in the literature. Additionally, Grad-CAM visualization was used to interpret and validate the decision-making process of the proposed model. The proposed model's performance was evaluated using the five-fold cross-validation method. The proposed model demonstrated superior performance with 99.50% accuracy, 99.47% precision, 99.52% recall and 99.49% F1 score. The results obtained show that the model outperforms the studies in the literature. Moreover, Grad-CAM visualizations demonstrate that the model effectively focuses on relevant regions of MRI images, thus improving interpretability and clinical reliability. A robust deep learning model for clinical decision support systems has been obtained by combining EfficientNetV2 and attention-based MLP-Mixer, providing high accuracy and interpretability in brain tumor classification.

In subjective assessment of image and video quality, observers rate or compare selected stimuli. Before calculating the mean opinion scores (MOS) for these stimuli from the ratings, it is recommended to identify and deal with outliers that may have given unreliable ratings. Several methods are available for this purpose, some of which have been standardized. These methods are typically based on statistics and sometimes tested by introducing synthetic ratings from artificial outliers, such as random clickers. However, a reliable and comprehensive approach is lacking for comparative performance analysis of outlier detection methods. To fill this gap, this work proposes and applies an empirical worst-case analysis as a general solution. Our method involves evolutionary optimization of an adversarial black-box attack on outlier detection algorithms, where the adversary maximizes the distortion of scale values with respect to ground truth. We apply our analysis to several hard and soft outlier detection methods for absolute category ratings and show their differing performance in this stress test. In addition, we propose two new outlier detection methods with low complexity and excellent worst-case performance. Software for adversarial attacks and data analysis is available.