Generative models are increasingly central to scientific workflows, yet their systematic use and interpretation require a proper understanding of their limitations through rigorous validation. Classic approaches struggle with scalability, statistical power, or interpretability when applied to high-dimensional data, making it difficult to certify the reliability of these models in realistic, high-dimensional scientific settings. Here, we propose the use of the New Physics Learning Machine (NPLM), a learning based approach to goodness-of-fit testing inspired by the Neyman-Pearson construction, to test generative networks trained on high-dimensional scientific data. We demonstrate the performance of NPLM for validation in two benchmark cases: generative models trained on mixtures of Gaussian models with increasing dimensionality, and a public end-to-end generator for the Large Hadron Collider called FlashSim, trained on jet data, typical in the field of high-energy physics. We demonstrate that the NPLM can serve as a powerful validation method while also providing a means to diagnose sub-optimally modeled regions of the data.

Detecting chemical modifications on RNA molecules remains a key challenge in epitranscriptomics. Traditional reverse transcription-based sequencing methods introduce enzyme- and sequence-dependent biases and fragment RNA molecules, confounding the accurate mapping of modifications across the transcriptome. Nanopore direct RNA sequencing offers a powerful alternative by preserving native RNA molecules, enabling the detection of modifications at single-molecule resolution. However, current computational tools can identify only a limited subset of modification types within well-characterized sequence contexts for which ample training data exists. Here, we introduce a model-free computational method that reframes modification detection as an anomaly detection problem, requiring only canonical (unmodified) RNA reads without any other annotated data. For each nanopore read, our approach extracts robust, modification-sensitive features from the raw ionic current signal at a site using the signature transform, then computes an anomaly score by comparing the resulting feature vector to its nearest neighbors in an unmodified reference dataset. We convert anomaly scores into statistical p-values to enable anomaly detection at both individual read and site levels. Validation on densely-modified \textit{E. coli} rRNA demonstrates that our approach detects known sites harboring diverse modification types, without prior training on these modifications. We further applyied this framework to dengue virus (DENV) transcripts and mammalian mRNAs. For DENV sfRNA, it led to revealing a novel 2'-O-methylated site, which we validate orthogonally by qRT-PCR assays. These results demonstrate that our model-free approach operates robustly across different types of RNAs and datasets generated with different nanopore sequencing chemistries.

Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods, primarily designed for classification tasks, are ineffective against the autoregressive nature and vast output space of LLMs, thereby suffering from poor performance and high latency. To address these limitations, we investigate the behavioral discrepancies between benign and back-doored LLMs in output space. We identify a critical phenomenon which we term sequence lock: a backdoored model generates the target sequence with abnormally high and consistent confidence compared to benign generation. Building on this insight, we propose ConfGuard, a lightweight and effective detection method that monitors a sliding window of token confidences to identify sequence lock. Extensive experiments demonstrate ConfGuard achieves a near 100% true positive rate (TPR) and a negligible false positive rate (FPR) in the vast majority of cases. Crucially, the ConfGuard enables real-time detection almost without additional latency, making it a practical backdoor defense for real-world LLM deployments.

These authors contributed equally to this work . Abstract: Brain - computer interfaces (BCIs) promise to extend human movement capabilities by enabling direct neural control of supernumerary effectors, yet integrating augmented commands with multi ple degrees of freedom without disrupting natural movement remains a k ey challenge. Here, we propose a tactile - encoded BCI that leverages sensory afferents through a novel tactile - evoked P300 paradigm, allowing intuitive and reliable decoding of supernumerary motor intentions even when superimposed with voluntary actions. The interface was evaluated in a multi - day experiment comprising of a single motor recognition task to validate baseline BCI performance and a dual task paradigm to assess the potential influence between the BCI and natural human movement . T he brain interface achieved real - time and reliable decoding of four supernumerary degrees of freedom, with significant performance improvement s after only three days of training. Importantly, after training, performance did not differ significantly b etween the single - and dual - BCI task conditions, and natural movement remained unimpaired during concurrent supernumerary control . Lastly, the interface was deployed in a movement augmentation task, demonstrating its ability to command two supernumerary robotic arms for functional assistance during bimanual tasks. These results establish a new neural interface paradigm for movement augmentation through stimulation of sensory afferents, expanding motor degrees of fr eedom without impairing natural movement . One - Sentence Summary: T actile - encoded neural interface enables intuitive control of supernumerary limbs without compromising natural human movement Main Text: INTRODUCTION Humans interact with their surroundings with remarkable dexterity and efficiency. Recent advances in robotics and neural interfaces hold the potential to increase these capabilities, enhancing human movement beyond its natural limits. Movement augmentation aims to increase the mechanical degrees of freedom (DoFs) an individual can exert over their surroundings ( 1), allowing movement tasks to be performed more efficiently or enable actions otherwise impossible with natural limbs alone, such as trimanual manipulation with a third arm ( 2) . A central challenge, however, lies in achieving practical control of supernumerary effectors (SEs) without compromising natural movement. Current strategies for augmenting DoFs often rely on augmentation by transfer, in which control of SEs is derived from the function of an existing body part, typically one that is task - irrelevant ( 1, 3, 4) .

Abstract--With the growing adoption of AI and machine learning systems in real-world applications, ensuring their fairness has become increasingly critical. There is relatively little research on fairness vulnerability, i.e., how an AI system's fairness can be intentionally compromised. In this work, we first provide a theoretical analysis demonstrating that a simple adversarial poisoning strategy is sufficient to induce maximally unfair behavior in naive Bayes classifiers. Our key idea is to strategically inject a small fraction of carefully crafted adversarial data points into the training set, biasing the model's decision boundary to disproportionately affect a protected group while preserving generalizable performance. T o illustrate the practical effectiveness of our method, we conduct experiments across several benchmark datasets and models. We find that our attack significantly outperforms existing methods in degrading fairness metrics across multiple models and datasets, often achieving substantially higher levels of unfairness with a comparable or only slightly worse impact on accuracy. Notably, our method proves effective on a wide range of models, in contrast to prior work, demonstrating a robust and potent approach to compromising the fairness of machine learning systems. Ensuring fairness in AI and machine learning systems is a critical concern alongside their growing real-world deployment.

Abstract--Integration of edge, cloud and space devices into a unified 3D continuum imposes significant challenges for client selection in federated learning systems. Traditional approaches rely on continuous monitoring and historical data collection, which becomes impractical in dynamic environments where satellites and mobile devices frequently change operational conditions. Furthermore, existing solutions primarily consider CPU-based computation, failing to capture complex characteristics of GPU-accelerated training that is prevalent across the 3D continuum. This paper introduces ProbSelect, a novel approach utilizing analytical modeling and probabilistic forecasting for client selection on GPU-accelerated devices, without requiring historical data or continuous monitoring. Extensive evaluation across diverse GPU architectures and workloads demonstrates that ProbSelect improves SLO compliance by 13.77% on average while achieving 72.5% computational waste reduction compared to baseline approaches.

Large Language Models (LLMs) have demonstrated their remarkable capabilities in document understanding. However, recent research reveals that LLMs still exhibit performance gaps in Document-level Relation Extraction (DocRE) as requiring fine-grained comprehension. The commonly adopted "extract entities then predict relations" paradigm in LLM-based methods leads to these gaps due to two main reasons: (1) Numerous unrelated entity pairs introduce noise and interfere with the relation prediction for truly related entity pairs. (2) Although LLMs have identified semantic associations between entities, relation labels beyond the predefined set are still treated as prediction errors. To address these challenges, we propose a novel Relation as a Prior (RelPrior) paradigm for LLM-based DocRE. For challenge (1), RelPrior utilizes binary relation as a prior to extract and determine whether two entities are correlated, thereby filtering out irrelevant entity pairs and reducing prediction noise. For challenge (2), RelPrior utilizes predefined relation as a prior to match entities for triples extraction instead of directly predicting relation. Thus, it avoids misjudgment caused by strict predefined relation labeling. Extensive experiments on two benchmarks demonstrate that RelPrior achieves state-of-the-art performance, surpassing existing LLM-based methods.

Securing Dew-Enabled Edge-of-Things (EoT) networks against sophisticated intrusions is a critical challenge. This paper presents HybridGuard, a framework that integrates machine learning and deep learning to improve intrusion detection. HybridGuard addresses data imbalance through mutual information based feature selection, ensuring that the most relevant features are used to improve detection performance, especially for minority attack classes. The framework leverages Wasserstein Conditional Generative Adversarial Networks with Gradient Penalty (WCGAN-GP) to further reduce class imbalance and enhance detection precision. It adopts a two-phase architecture called DualNetShield to support advanced traffic analysis and anomaly detection, improving the granular identification of threats in complex EoT environments. HybridGuard is evaluated on the UNSW-NB15, CIC-IDS-2017, and IOTID20 datasets, where it demonstrates strong performance across diverse attack scenarios and outperforms existing solutions in adapting to evolving cybersecurity threats. This approach establishes HybridGuard as an effective tool for protecting EoT networks against modern intrusions.

Deep learning vision systems are increasingly deployed in safety-critical domains such as healthcare, yet they remain vulnerable to small adversarial patches that can trigger mis-classifications. Most existing defenses assume a single patch and fail when multiple localized disruptions occur, the type of scenario adversaries and real-world artifacts often exploit. We propose Filtered-ViT, a new vision transformer architecture that integrates SMART V ector Median Filtering (SMART - VMF), a spatially adaptive, multi-scale, robustness-aware mechanism that enables selective suppression of corrupted regions while preserving semantic detail. On ImageNet with LaV AN multi-patch attacks, Filtered-ViT achieves 79.8% clean accuracy and 46.3% robust accuracy under four simultaneous 1% patches, outperforming existing defenses. Beyond synthetic benchmarks, a real-world case study on radiographic medical imagery shows that Filtered-ViT mitigates natural artifacts such as occlusions and scanner noise without degrading diagnostic content. This establishes Filtered-ViT as the first transformer to demonstrate unified robustness against both adversarial and naturally occurring patch-like disruptions, charting a path toward reliable vision systems in truly high-stakes environments.

Artificial Intelligence (AI) models have demonstrated expert-level performance in melanoma detection, yet their clinical adoption is hindered by performance disparities across demographic subgroups such as gender, race, and age. Previous efforts to benchmark the performance of AI models have primarily focused on assessing model performance using group fairness metrics that rely on the Area Under the Receiver Operating Characteristic curve (AUROC), which does not provide insights into a model's ability to provide accurate estimates. In line with clinical assessments, this paper addresses this gap by incorporating calibration as a complementary benchmarking metric to AUROC-based fairness metrics. Calibration evaluates the alignment between predicted probabilities and observed event rates, offering deeper insights into subgroup biases. We assess the performance of the leading skin cancer detection algorithm of the ISIC 2020 Challenge on the ISIC 2020 Challenge dataset and the PROVE-AI dataset, and compare it with the second and third place models, focusing on subgroups defined by sex, race (Fitzpatrick Skin Tone), and age. Our findings reveal that while existing models enhance discriminative accuracy, they often over-diagnose risk and exhibit calibration issues when applied to new datasets. This study underscores the necessity for comprehensive model auditing strategies and extensive metadata collection to achieve equitable AI-driven healthcare solutions. All code is publicly available at https://github.com/bdominique/testing_strong_calibration.