Search Results (154)

The Federal Institute of Material Research and Testing has performed many impact tests, from very small laboratory tests to very big “free-field” tests with heavy containers on stiff foundations. The first measurements have been done on a big foundation where it should be guaranteed that the foundation is rigid and the container is tested properly. Later, a smaller drop-test facility has been built on the ground inside an existing building. It had to be controlled by prediction and measurements to ensure that the drop test will not damage the building. Tests from different heights on soft, medium, and stiff targets have been done to find out rules which allow to identify acceptable and unacceptable drop tests. Later, the biggest drop test facility has been built for masses up to 200 t. It was necessary for the design of the foundation to estimate the forces which occur during the drop tests. In addition, the acceptable tests should be selected and controlled by measurements where the impact duration is important. Different sensors, accelerometers, accelerometers with mechanical filters, geophones (velocity transducers), strain gauges, and pressure cells have been applied for these tasks. Signal transformations and model calculations have been used to check and understand the dynamic measurements. The simplest law is the conservation of the momentum which is a good approximation if the impact is short. If the soil under the foundation has an influence on the deceleration of the container, the maximum foundation velocity is lower than the simple estimation. Full article

Federated data spaces, established through initiatives such as IDSA and GAIA-X, enable organizations to share and monetize datasets under contractual terms. However, enforcing these contracts—particularly detecting unauthorized reuse or modification of datasets—remains an open challenge. We present the Off-Platform Contract Inspector, a component of the PISTIS framework, that implements a modular similarity-detection pipeline combining path-value Jaccard similarity, field-aware type-specific comparisons, and sentence-embedding-based semantic analysis across structured, semi-structured, and unstructured datasets. This contributes as follows: (i) an Inverse Document Frequency (IDF)-weighted structural similarity mechanism that discounts common domain vocabulary via Inverse Document Frequency weighting over the data space catalog, combined with a schema-evidence-gated fusion that reduces false positives from domain vocabulary overlap; (ii) an adaptive threshold optimization mechanism that learns modality-specific fusion weights and decision thresholds via cross-validated grid search; and (iii) a privacy-preserving similarity layer based on MinHash Locality-Sensitive Hashing signatures, Bloom filters with OR folding alignment, and Laplace noise for differential privacy, enabling cross-organizational dataset comparison without exposing raw data. Further, we contribute a threat taxonomy of seven dataset modification types ordered by detection difficulty, and evaluate the system on dataset pairs derived from real-world datasets across three smart-city application domains (Mobility, Energy, Automotive), with controlled augmentations applied to model adversarial behaviors. The IDF-weighted pipeline achieves high precision on intra-domain hard negatives—pairs of different tables from the same data space that share domain vocabulary—where text-similarity baselines produce false positives. The adaptive scheme learns per-modality fusion weights via cross-validated grid search. The privacy-preserving mode operates without accessing raw data and runs noticeably faster than the full pipeline, enabling screening while preserving data confidentiality. Full article

As renewable penetration in data-center power supply increases, stochastic renewable output can cause tie-line power fluctuations between data centers (DCs) and the utility grid. This paper proposes a privacy-preserving multi-time-scale tie-line power smoothing method for multiple DCs. A two-stage first-order low-pass filter decomposes tie-line fluctuations into high- and low-frequency regulation targets. Server task shifting tracks the high-frequency target, while uninterruptible power supply (UPS) regulation compensates the low-frequency residual under practical energy and power constraints. Second, a federated adaptive proximal policy optimization (Fed-AdaPPO) framework is developed. Proximal policy optimization (PPO) provides stable policy optimization in the continuous action space, and the upper confidence bound (UCB)-guided adaptive exploration improves task-shifting exploration. Critically, only Critic gradients are aggregated across DCs; Actor networks, raw workload data, and user-sensitive information remain local. This design reduces the risk of exposing local state-action mappings. Results show that coordinated server-cluster and UPS regulation reduces the standard deviation of tie-line power by at least 33.4% while maintaining service quality and data privacy. Full article

Anthropic’s April 2026 Claude Mythos Preview release established a new operational threat category: frontier AI systems whose extended-context reasoning, recursive self-correction, native system-tool integration, and agentic scaffolding render dominant AI safety paradigms—RLHF, output filtering, contractual access vetting, human-in-the-loop supervision—insufficient as sole controls. This paper develops a defense-in-depth reference architecture against that category, structured around four named contributions: a five-indicator operational definition of the Mythos-class (capability conjoined with scaffold, access pattern, autonomy depth, and persistence); the Mythos-Class Posture Rubric (MCPR), a three-tier detection framework spanning evaluation, deployment, and runtime with explicit routing to mitigation layers; a four-layer mitigation stack comprising the Vetted-Access Operational Pattern (VAOP), Authority-Bound Output Release (ABOR) cryptographically grounded in FIPS 203/204/205 post-quantum primitives, and the Compute-Plane Isolation Profile (CPIP); and an integrated architecture that crosswalks to the NIST AI Risk Management Framework, NIST Cybersecurity Framework 2.0, and CISA Zero Trust Maturity Model 2.0. The architecture is applied to three deployment surfaces—post-quantum cryptography migration, federal AI supply-chain assurance, and critical-infrastructure operational technology defense—demonstrating that the four contributions generalize across heterogeneous operational contexts. The contribution is a reference design rather than a deployed system; limitations, falsifiability criteria, and a research agenda for empirical refinement are developed. Full article

Federated edge learning on microcontrollers (MCUs) enables privacy-preserving adaptation, but on-device training faces a hardware tradeoff: fitting backpropagation into a limited static random-access memory (SRAM) often relies on on-chip flash as auxiliary storage, while repeated parameter persistence rapidly consumes finite program/erase (P/E) endurance. This paper proposes TinySLFL, a flash-endurance-aware federated learning framework for resource-constrained MCUs. On the client, layer-wise training bounds the peak SRAM usage to one layer, and delayed aggregation keeps intermediate updates in SRAM so that each communication round incurs only one flash persistence. On the server, dynamic aggregation combines loss-aware freezing with proxy-accuracy-guided filtering to improve the robustness under non-independently and identically distributed (Non-IID) data while suppressing unnecessary rounds. Experiments on CIFAR-10 and SVHN under a severe Dirichlet label skew and on a naturally heterogeneous FEMNIST showed, in a server-side simulation, that TinySLFL reduces the cumulative protocol-level erase-block operations (EOs) required to reach a common target accuracy by 97.8–98.6% relative to sequential layer training (SLT) and improves the mean Top-1 accuracy by up to 5.24 percentage points over the same ResNet-8 backbone in a five-seed evaluation. The power, latency, SRAM, and deployment feasibility were reported from actual ESP32-S3 measurements. These results demonstrate durable federated learning for extreme-edge MCUs. Full article

Antivirus systems have evolved from static pattern matchers into complex algorithmic ecosystems that encapsulate the broader logic of modern cybersecurity. This review deconstructs their internal architecture, tracing the transition from deterministic string-matching automata to probabilistic, behavioral, and cloud-assisted paradigms. Foundational modules such as scanners, heuristic analyzers, behavioral monitors, and sandbox environments operate as interconnected computational strata, forming adaptive feedback loops that mirror principles of distributed intelligence. Signature-based methods, such as Aho-Corasick, Boyer-Moore, and Wu-Manber, remain core to real-time filtering, while probabilistic reasoning through Bayesian inference, Markov modeling, and Hidden Markov Models extends detection to polymorphic and metamorphic threats. Behavioral analysis, empowered by Support Vector Machines, deep neural architectures, and temporal models, enables semantic inference over system-call graphs and runtime telemetry. Moreover, cloud-assisted frameworks integrate federated learning and global reputation graphs, which transform detection into a collective intelligence process. Full article

Colorectal cancer (CRC) remains one of the leading causes of cancer-related mortality worldwide, with prognosis critically dependent on the stage at diagnosis. Traditional tissue biopsy presents well-known limitations, including tumor heterogeneity and invasiveness. Liquid biopsy, encompassing the analysis of circulating tumor DNA (ctDNA), circulating tumor cells (CTCs), exosomes, and other cell-free biomarkers, has emerged as a transformative approach for non-invasive tumor profiling. This comprehensive narrative review outlines the recent evidence published on the current state and future perspectives of liquid biopsy in CRC, with a focused emphasis on the role of artificial intelligence (AI), machine learning (ML), and deep learning (DL) in data analysis and clinical translation. Methods: A narrative review of the literature was conducted by searching PubMed/MEDLINE, EMBASE, and ClinicalTrials.gov for articles published between January 2020 and January 2026, using a predefined Boolean search string combining terms related to liquid biopsy biomarkers, colorectal cancer, and artificial intelligence methodologies. Filters were applied to include only English-language human studies. Additional relevant sources were consulted to ensure comprehensive coverage of the available literature. Liquid biopsy platforms, particularly ctDNA sequencing and methylation profiling, demonstrate increasing clinical utility across the CRC care continuum from population screening to post-surgical minimal residual disease (MRD) detection and real-time therapy monitoring. AI-driven analytical frameworks, including Random Forest, Convolutional Neural Networks, LSTM models, and more recently Large Language Models (LLMs), substantially augment the sensitivity and specificity of liquid biopsy interpretation, enabling multimodal data integration. The convergence of liquid biopsy technology and AI-driven analytics represents a paradigm shift toward precision oncology in CRC. Remaining challenges include analytical standardization, model explainability, regulatory harmonization, and equitable access. Future integration of federated learning frameworks and LLM-based clinical decision support tools will be essential for responsible clinical translation. Full article

To improve the state-of-charge (SOC) estimation accuracy of sodium-ion batteries under complex operating conditions, this paper proposes a particle swarm optimization-based heterogeneous adaptive extended Kalman filter. A hardware-in-the-loop (HIL) validation platform is also established to reproduce the sampling-chain constraints of a practical battery management system. In addition, a second-order equivalent circuit model (ECM) serves to characterize battery dynamics and generate validation data. Within this framework, the degradation in estimation performance from the theoretical environment to practical hardware execution is quantitatively analyzed. The feasibility of using ECM-generated data for SOC estimation algorithm validation is also evaluated. Using measured Federal Urban Driving Schedule data at 25 °C, the proposed method achieves high estimation accuracy and stable convergence in both environments. Specifically, the mean absolute error and root-mean-square error in the theoretical environment are 0.11% and 0.25%, respectively. Under HIL conditions, the corresponding values are 0.60% and 0.63%. Additional tests under different temperatures and composite disturbance conditions further verify the adaptability and robustness of the proposed algorithm. The results also show that practical hardware constraints introduce non-negligible performance degradation. In addition, ECM-generated data remain highly consistent with measured data in terms of error-evolution trends. Therefore, ECM-generated data can serve as a feasible validation data source for SOC estimation algorithm performance evaluation and rapid validation. Full article

To address statistical heterogeneity and update-level privacy risks in federated learning for geospatial data, this paper proposes a hierarchically decoupled collaborative framework that integrates client-side privacy perturbation with server-side consistency-aware aggregation, while incorporating governance as a system-level support module. Under strong non-IID conditions, the proposed soft-weight aggregation strategy mitigates update mismatch and improves convergence stability without hard filtering legitimate but distributionally shifted client contributions. Meanwhile, the risk-aware perturbation mechanism adaptively adjusts clipping and noise strength across clients to better balance privacy protection and model utility. An on-chain governance and off-chain training coordination mechanism is further introduced to support auditable and traceable collaboration without interfering with the main optimization process. Experimental results on EuroSAT_RGB with ResNet-18 show that the proposed design achieves more stable training and better overall performance than the compared baselines, especially under severe heterogeneity. These findings highlight the value of jointly considering privacy-aware perturbation and consistency-aware aggregation for improving training stability and preserving utility in geospatial federated learning under statistically heterogeneous settings. Full article

Deep learning-based recommendation systems are highly vulnerable to data poisoning attacks, where adversaries manipulate user interactions to degrade model integrity. We hypothesize that combining an active robust loss with a passive GAN-based detection will significantly reduce poisoning impact in recommendation systems without sacrificing utility. We propose a robust and adaptive dual-defense framework: the active defense integrates a crafted loss function to mitigate poisoning effects while maintaining model performance. The passive defense employs a Generative Adversarial Network (GAN)-based detection model to identify and filter poisoned data, enhancing detection accuracy and system security. The framework supports classical matrix factorization (MF) model and large language model (LLM)-based pipelines and scales to large datasets. Extensive experiments across multiple real-world datasets at varying poison rates show that our method outperforms representative defenses, consistently reducing attack success without sacrificing recommendation quality. The framework also admits a federated instantiation, where robust training and GAN-based detection run on clients and only privacy-preserving summaries are aggregated. The proposed method significantly improves the robustness and adaptability of recommendation systems under data poisoning attacks. Full article

Federated learning (FL) enables collaborative model training across distributed devices and robotic systems while preserving data privacy, making it well-suited for swarm robotics and edge-device-powered intelligence. However, FL remains vulnerable to adversarial behaviors such as data and model poisoning, particularly in real-world deployments where detection methods must operate under strict computational and communication constraints. This paper presents a practical, real-world federated learning framework that enhances robustness to adversarial agents in a ROS2-based edge-device swarm environment. The proposed system integrates the Federated Averaging (FedAvg) algorithm with a lightweight average cosine similarity-based filtering method to detect and suppress harmful model updates during aggregation. Unlike prior work that primarily evaluates poisoning defenses in simulated environments, this framework is implemented and evaluated on physical hardware, consisting of a laptop-based aggregator and multiple Raspberry Pi worker nodes. A convolutional neural network (CNN) based on the MobileNetV3-Small architecture is trained on the MNIST dataset, with one worker executing a sign-flipping model poisoning attack. Experimental results show that FedAvg alone fails to maintain meaningful model accuracy under adversarial conditions, resulting in near-random classification performance with a final global model accuracy of 11% and a loss of 2.3. In contrast, the integration of cosine similarity filtering demonstrates effective detection of sign-flipping model poisoning in the evaluated ROS2 swarm experiment, allowing the global model to maintain model accuracy of around 90% and loss around 0.37, which is close to baseline accuracy of 93% of the FedAvg algorithm only under no attack with a very minimal increase in loss, despite the presence of an attacker. The proposed method also maintains a false positive rate (FPR) of around 0.01 and a false negative rate (FNR) of around 0.10 of the global model in the presence of an attacker, which is a minimal difference from the baseline FedAvg-only results of around 0.008 for FPR and 0.07 for FNR. Additionally, the proposed method of FedAvg + cosine similarity filtering maintains computational statistics similar to baseline FedAvg with no attacker. Baseline results show an average runtime of about 34 min, while our proposed method shows an average runtime of about 35 min. Also, the average size of the global model being shared among workers remains consistent at around 7.15 megabytes, showing little to no increase in message payload sizes between baseline results and our proposed method. These results demonstrate that computationally lightweight cosine similarity-based detection methods can be effectively deployed in real-world, resource-constrained robotic swarm environments, providing a practical path toward improving robustness in real-world federated learning deployments beyond simulation-based evaluation. Full article

Underwater Acoustic Sensor Networks (UASNs) are pivotal for environmental monitoring, surveillance, and marine data collection. However, their open and largely unattended operational settings, constrained communication capabilities, limited energy resources, and susceptibility to insider attacks make it difficult to achieve safe, secure, and efficient collaborative learning. Federated learning (FL) offers a privacy-preserving method for decentralized model training but is inherently vulnerable to Byzantine threats and malicious participants. This paper proposes trust-aware FL for underwater sensor networks (TAFL-UWSN), a trust-aware FL framework designed to improve security, reliability, and energy efficiency in UASNs by incorporating trust evaluation directly into the FL process. The goal is to mitigate the impact of adversarial nodes while maintaining model performance in low-resource underwater environments. TAFL-UWSN integrates continuous trust scoring based on packet forwarding reliability, sensing consistency, and model deviation. Trust scores are used to weight or filter model updates both at the node level and the edge layer, where Autonomous Underwater Vehicles (AUVs) act as mobile aggregators. A trust-aware federated averaging algorithm is implemented, and extensive simulations are conducted in a custom Python-based environment, comparing TAFL-UWSN to standard FedAvg and Byzantine-resilient FL approaches under various attack conditions. TAFL-UWSN achieved a model accuracy exceeding 92% with up to 30% malicious nodes while maintaining a false positive rate below 5.5%. Communication overhead was reduced by 28%, and energy usage per node dropped by 33% compared to baseline methods. The TAFL-UWSN framework demonstrates that integrating trust into FL enables secure, efficient, and resilient underwater intelligence, validating its potential for broader application in distributed, resource-constrained environments. Full article

Byzantine failures remain a critical threat to Federated Learning (FL), where malicious clients inject adversarial updates to disrupt global model convergence. From the perspective of symmetry, benign client updates typically exhibit statistical symmetry around the global consensus, whereas Byzantine attacks function as “symmetry-breaking” events that introduce skewness and distributional anomalies. Existing defenses often rely on unrealistic assumptions or fail to capture these asymmetric deviations under high-dimensional non-IID settings. In this paper, we propose a symmetry-aware Byzantine-resilient FL framework driven by a Dual-Channel Attention-Driven Anomaly Detector (DAAD). Specifically, DAAD transforms inter-client behaviors into geometrically symmetric interaction matrices—encoding Gradient Cosine Similarities and Loss Euclidean Distances—to construct dual-channel spatial representations. These representations are processed via a Convolutional Neural Network (CNN) enhanced with Squeeze-and-Excitation (SE) attention blocks, which leverage the inherent symmetry of benign consensus to extract robust adversarial signatures. The detector is pre-trained offline on a synthetic dataset incorporating a diverse portfolio of simulated attacks (e.g., Gaussian noise and label flipping). Crucially, this pre-trained model is seamlessly embedded into the online FL loop to filter updates without requiring ground-truth labels. By jointly encoding client behaviors and learning cross-modal attack signatures, our framework enables reliable detection even when over half of the clients are Byzantine. Extensive experiments on MNIST, CIFAR-10, and FEMNIST datasets demonstrate that DAAD consistently outperforms existing robust aggregation baselines in both anomaly detection accuracy and global model performance, especially under high Byzantine ratios and non-IID conditions. Full article

Federated Learning (FL) represents a promising paradigm for collaborative model training across numerous devices, preserving data locality and offering potential privacy benefits for industries such as finance, healthcare, and Internet of Things (IoT). Nonetheless, real-world deployments of FL encounter challenges arising from dynamic and diverse environments, which adversely affect training speed and model convergence. To address these issues, this paper introduces FedDCS, an adaptive federated learning framework that effectively manages resources during training through two primary innovations. First, it establishes a reliable method for predicting client training durations, estimating completion times while filtering noise and detecting performance variations. Second, it implements a two-stage adaptive waiting strategy that dynamically determines the optimal timing and selection of client batches for aggregation, thereby balancing collection efficiency with model accuracy. This approach optimizes the trade-off between efficiency and accuracy in heterogeneous settings. Extensive evaluations on datasets such as Fashion-MNIST and CIFAR-10/100, incorporating simulated device and data heterogeneity, demonstrate that FedDCS consistently achieves superior time efficiency and higher global model accuracy compared to state-of-the-art (e.g., synchronous, asynchronous, and semi-asynchronous) baselines. Its robustness and versatility render it effective across various complex and heterogeneous environments. Full article

Background/Objectives: Isocitrate dehydrogenase (IDH) mutation is a key prognostic indicator in diffuse gliomas; however, it is clinically determined from invasive tissue sampling. Non-invasive preoperative identification of IDH mutation from routine anatomical MRI could support treatment decision making. This study evaluated deep learning models for IDH mutation detection using routine anatomical MRI (post-contrast T1-weighted (T1c), T2-weighted, and fluid attenuated inversion recovery (FLAIR) MRI) and quantified how tumor-focused image preprocessing and different training schemes, centralized learning (CL) versus federated learning (FL) with alternative aggregation strategies, affected model performance. Methods: Anatomical MRI from 501 diffuse glioma patients in the UCSF Preoperative Diffuse Glioma MRI (UCSF-PDGM) dataset was analyzed using a deep learning classifier built on a 2D U-Net encoder, with age and sex included as covariates. Two methods of tumor-focused image preprocessing, Naïve Soft Filtering (NSF) and Gradient-Based Soft Filtering (GBSF), were compared. Centralized learning (CL) was benchmarked against federated learning (FL) using Federated Averaging (FA) and Federated Trimmed Mean (FTM) aggregation strategies. Model performance was compared in terms of accuracy, precision, recall, F1 score, specificity, and the area under the receiver operating characteristic curve (ROC-AUC). Results: The CL model with NSF achieved the best test performance (accuracy = 0.949, F1 = 0.951, ROC-AUC = 0.971), with NSF consistently outperforming GBSF. FL’s performance decreased relative to CL’s, but the FA strategy outperformed FTM (FTM accuracy = 0.915 vs. FA accuracy = 0.949), which indicates that the FL aggregation strategy has an influence on model performance. Conclusions: Deep learning applied to routine anatomical MRI could classify IDH mutation status with high accuracy. Context-preserving image preprocessing with NSF substantially improved performance across training schemes. FL provides a privacy-preserving alternative to CL, but incurs a measurable performance degradation that is sensitive to the choice of aggregation strategy. Full article