Unknown Network Research Articles

Power flow distribution identification via machine learning algorithm and distributed resource clearing method

Abstract Under the background of dual carbon, a large number of distributed new energy sources are connected to the demand side, which leads to great risks in the operation of the power system. As an effective solution, distributed power transaction still has problems, such as high clearing time, unknown low-voltage distribution network structure, and resource scheduling ignoring user needs. Therefore, this paper proposes an optimal regulation method of demand-side resources based on distributed transactions. Based on the historical operation data of the distribution network, the eXtreme Gradient Boosting (XGBoost) algorithm is used to study the relationship between node injection power, node voltage, and node-side line power flow. It is also used to check the results of distributed transactions and design a market mechanism for rapid clearing and settlement of distributed transactions. The results of an example show that the identification of power flow distribution in a distribution network based on reinforcement learning can meet the security check requirements of distributed transaction results.

Causal message-passing for experiments with unknown and general network interference

Randomized experiments are a powerful methodology for data-driven evaluation of decisions or interventions. Yet, their validity may be undermined by network interference. This occurs when the treatment of one unit impacts not only its outcome but also that of connected units, biasing traditional treatment effect estimations. Our study introduces a framework to accommodate complex and unknown network interference, moving beyond specialized models in the existing literature. Our framework, termed causal message-passing, is grounded in high-dimensional approximate message-passing methodology. It is tailored for multiperiod experiments and is particularly effective in settings with many units and prevalent network interference. The framework models causal effects as a dynamic process where a treated unit's impact propagates through the network via neighboring units until equilibrium is reached. This approach allows us to approximate the dynamics of potential outcomes over time, enabling the extraction of valuable information before treatment effects reach equilibrium. Utilizing causal message-passing, we introduce a practical algorithm to estimate the total treatment effect, defined as the impact observed when all units are treated compared to the scenario where no unit receives treatment. We demonstrate the effectiveness of this approach across five numerical scenarios, each characterized by a distinct interference structure.

Network mechanisms of ongoing brain activity’s influence on conscious visual perception

Sensory inputs enter a constantly active brain, whose state is always changing from one moment to the next. Currently, little is known about how ongoing, spontaneous brain activity participates in online task processing. We employed 7 Tesla fMRI and a threshold-level visual perception task to probe the effects of prestimulus ongoing brain activity on perceptual decision-making and conscious recognition. Prestimulus activity originating from distributed brain regions, including visual cortices and regions of the default-mode and cingulo-opercular networks, exerted a diverse set of effects on the sensitivity and criterion of conscious recognition, and categorization performance. We further elucidate the mechanisms underlying these behavioral effects, revealing how prestimulus activity modulates multiple aspects of stimulus processing in highly specific and network-dependent manners. These findings reveal heretofore unknown network mechanisms underlying ongoing brain activity’s influence on conscious perception, and may hold implications for understanding the precise roles of spontaneous activity in other brain functions.

Knowing the unknowns: Network traffic detection with open-set semi-supervised learning

Network traffic classification plays a crucial role in network security and network quality of service. The new emerging traffic data in the real world is unlabeled and may contain unknown classes, which introduces the problem of identifying unknown-class traffic in unlabeled data. However, existing deep learning-based methods either rely on large amounts of labeled data or assume the labeled and unlabeled data share the common label space. Therefore, they are unable to identify unknown traffic, resulting in decreased detection accuracy. This paper introduces DivinEye, a novel method for unknown network traffic detection based on open-set semi-supervised learning. DivinEye utilizes a small quantity of labeled data and a large amount of unlabeled data to train the model, achieving the ability to identify known classes accurately while also detecting unknown ones. To leverage incoming unlabeled traffic, DivinEye employs open-set semi-supervised techniques to select known-class data from unlabeled data to optimize the known traffic detection model. To detect unknown traffic, DivinEye combines the known traffic classifier and multi-binary classifier to construct an unknown traffic detection model, generating auxiliary targets for all unlabeled data as supervision to train the model. Trace-driven experiments demonstrate that DivinEye outperforms state-of-the-art methods by a large margin.

Sampling unknown large networks restricted by low sampling rates

Graph sampling plays an important role in data mining for large networks. Specifically, larger networks often correspond to lower sampling rates. Under the situation, traditional traversal-based samplings for large networks usually have an excessive preference for densely-connected network core nodes. Aim at this issue, this paper proposes a sampling method for unknown networks at low sampling rates, called SLSR, which first adopts a random node sampling to evaluate a degree threshold, utilized to distinguish the core from periphery, and the average degree in unknown networks, and then runs a double-layer sampling strategy on the core and periphery. SLSR is simple that results in a high time efficiency, but experiments verify that the proposed method can accurately preserve many critical structures of unknown large scale-free networks with low sampling rates and low variances.

Enhanced Network Security Protection through Data Analysis and Machine Learning: An Application of GraphSAGE for Anomaly Detection and Operational Intelligence

With the Internet's rapid expansion, network security challenges have become increasingly complex and prominent. Traditional protection methods, largely dependent on predefined rules and patterns, demonstrate limited effectiveness against sophisticated and unknown network attacks, failing to harness the full potential of extensive network data. This study addresses the challenges faced by modern cybersecurity, particularly the limitations of traditional defense methods in countering unknown and complex attacks, by proposing a solution that integrates data analysis and machine learning technologies. The focus of this research is placed on network security anomaly detection as well as on intelligent network operations and maintenance exception management based on graph network algorithms, aiming to enhance security defense capabilities and operational efficiency. Specifically, the main contributions and innovations of this paper include: 1. Innovations in sampling, aggregation, and loss functions within the Graph Sample and Aggregation (GraphSAGE) model to improve the accuracy and robustness of the model for network anomaly detection; 2. The introduction of a novel network anomaly root cause analysis and localization model, which, combined with an optimized root cause likelihood assessment method and search scheme, significantly enhances the speed and accuracy of anomaly localization; 3. The design of an integrated decision support system that can automatically adjust protection strategies as network conditions change, achieving a high level of automation and intelligence in cybersecurity management. This work not only provides effective technical support for network security protection but also opens new avenues for future cybersecurity research.

IDG-SemiAD: An Immune Detector Generation-Based Collaborative Learning Scheme for Semi-supervised Anomaly Detection in Industrial Cyber-physical Systems

Anomaly detection is a critical line of defense to ensure the network security of industrial cyber-physical systems. However, a significant issue in the anomaly detection is the insufficient labels of anomaly classes. With emergence of the new and unknown network attacks, accurately labeling these attacks can be a costly task. The issue of inadequate labeling may negatively impact the detection performance of many existing anomaly detection methods. To meet this gap, this paper proposes a semi-supervised collaborative learning paradigm called IDG-SemiAD, based on an immune detector generation algorithm. First, we design an immune detector generation algorithm based on a chaos map to generate abnormal samples from self-samples. Then, these abnormal samples are combined with self-samples and given specific labels to form a new training set. Finally, the LightGBM classifier is used for training and detection. Experiments on the widely used public dataset BATADAL show that the proposed IDG-SemiAD outperforms the classical v-detector method in terms of recall and f-score, with improvements of 8.2% and 8%, respectively, and outperforms deep learning-based anomaly detection methods, with a maximum improvements of up to 89.7% and 59.5% respectively.

A bit rate condition for feedback stabilization of uncertain switched systems with external disturbances based on event triggering

AbstractThis paper studies the input‐to‐state stability of an uncertain switched linear system with external disturbances, whose feedback loop is closed over a digital communication network. In the network, only a finite bit rate can be provided to transmit the feedback signal and unknown network delay always exists. By using reachable set approximation and propagation methods, it can well handle with the effects of model uncertainty, external disturbances and network delay on the stability of the system. To save network resources, event‐triggered sampling is taken here. Under the event‐triggered sampling strategies, a new encoder is proposed, which consumes less feedback bits than the conventional time‐triggered encoders. It is proven that even in the existence of model uncertainty, external disturbances and network delay, the proposed event‐triggered sampling strategies require a lower feedback bit rate to stabilize the switched system than conventional periodic sampling methods.

Towards Transferable Adversarial Attacks with Centralized Perturbation

Adversarial transferability enables black-box attacks on unknown victim deep neural networks (DNNs), rendering attacks viable in real-world scenarios. Current transferable attacks create adversarial perturbation over the entire image, resulting in excessive noise that overfit the source model. Concentrating perturbation to dominant image regions that are model-agnostic is crucial to improving adversarial efficacy. However, limiting perturbation to local regions in the spatial domain proves inadequate in augmenting transferability. To this end, we propose a transferable adversarial attack with fine-grained perturbation optimization in the frequency domain, creating centralized perturbation. We devise a systematic pipeline to dynamically constrain perturbation optimization to dominant frequency coefficients. The constraint is optimized in parallel at each iteration, ensuring the directional alignment of perturbation optimization with model prediction. Our approach allows us to centralize perturbation towards sample-specific important frequency features, which are shared by DNNs, effectively mitigating source model overfitting. Experiments demonstrate that by dynamically centralizing perturbation on dominating frequency coefficients, crafted adversarial examples exhibit stronger transferability, and allowing them to bypass various defenses.

Nonlinear network-based quantitative trait prediction from biological data

Abstract Quantitatively predicting phenotypic variables using biomarkers is a challenging task for several reasons. First, the collected biological observations might be heterogeneous and correspond to different biological mechanisms. Second, the biomarkers used to predict the phenotype are potentially highly correlated since biological entities (genes, proteins, and metabolites) interact through unknown regulatory networks. In this paper, we present a novel approach designed to predict multivariate quantitative traits from biological data which address the 2 issues. The proposed model performs well on prediction but it is also fully parametric, with clusters of individuals and regulatory networks, which facilitates the downstream biological interpretation.

Fault-tolerant unicast paths constructive algorithms in a family of recursive networks

ABSTRACT In parallel and distributed systems, interconnection networks and data center networks are two crucial networks. They are also crucial parts of high-performance computing and cloud computing services. With the rapid growth of high-performance computing and cloud computing, both networks are growing in size. At the same time, vertex faults are unavoidable. In computer/communication networks, unicast refers to one-to-one communication between the source vertex and the destination vertex. Fault-tolerant routing of vertices in networks is an important problem that has been widely discussed. In this paper, for a class of recursive networks with less than g -restrict connectivity fault vertices and each fault-free vertex having at least g fault-free neighbors, we provide a fault-tolerant unicast path design algorithm in this study. The algorithm’s correctness is then demonstrated and its time complexity is analyzed. In addition, the results obtained can be used for unknown and known networks, including the dragonfly network, DCell, and generalized DCell.

Unknown, Atypical and Polymorphic Network Intrusion Detection: A Systematic Survey

Unknown, Atypical and Polymorphic Network Intrusion Detection: A Systematic Survey

Fuzzy-Boosted Event-Triggered Tracking Control of Unknown Nonlinear Networked Systems: A PSO-Driven RL Approach

Fuzzy-Boosted Event-Triggered Tracking Control of Unknown Nonlinear Networked Systems: A PSO-Driven RL Approach

Intelligent Renewable Energy Agent‐Based Distributed Control Design for Frequency Regulation and Economic Dispatch

The Distributed Renewable Energy Sources (DRESs) integrate hybrid microgrid and prosumer activities that constitute a dynamic system characterized by unknown network parameters. The dynamic system faces challenges, such as intermittent power supply due to low inertia, renewable intermittence, plug‐and‐play prosumer activities, network topology variations, and a lack of constraint handling. These complexities pose significant issues in designing effective control for frequency regulation and consensus‐based economic load dispatch (ELD) within DRES to meet varying load demands. To address the above challenges, this research employs a machine learning‐based distributed multiagent consensus design that offers a rapid and robust approach, mitigating the limitations associated with the Distributed Average Integral (DAI) control design. The proposed multiagent scheme empowers the successful implementation of ELD and frequency regulation, accommodating the intermittent DRES, diverse network topologies, and the dynamic plug‐and‐play activities of prosumers. Moreover, an optimization‐based DAI tuning model is introduced to overcome tuning limitations. Intelligent renewable energy agents are trained through machine learning‐based regression models that use root mean square error metrics for performance evaluations. The intelligent agents employ DAI control to overcome inherent limitations. The effectiveness of the machine learning‐based DAI is thoroughly evaluated using the DRES‐based IEEE 14‐bus hybrid microgrid system. The quantitative results prove its efficacy in addressing the complex challenges of integrated microgrid dynamics.

Novel markers and networks related to restored skeletal muscle transcriptome after bariatric surgery.

The aim of this study was to discover novel markers underlying the improvement of skeletal muscle metabolism after bariatric surgery. Skeletal muscle transcriptome data of lean people and people with obesity, before and 1 year after bariatric surgery, were subjected to weighted gene co-expression network analysis (WGCNA) and least absolute shrinkage and selection operator (LASSO) regression. Results of LASSO were confirmed in a replication cohort. The expression levels of 440 genes differing between individuals with and without obesity were no longer different 1 year after surgery, indicating restoration. WGCNA clustered 116 genes with normalized expression in one major module, particularly correlating to weight loss and decreased plasma free fatty acids (FFA), 44 of which showed an obesity-related phenotype upon deletion in mice. Among the genes of the major module, 105 represented prominent markers for reduced FFA concentration, including 55 marker genes for decreased BMI in both the discovery and replication cohorts. Previously unknown gene networks and marker genes underlined the important role of FFA in restoring muscle gene expression after bariatric surgery and further suggest novel therapeutic targets for obesity.

Reconstruction and Layer Division of Unknown Multilayer Networks

Reconstruction and Layer Division of Unknown Multilayer Networks

A Compositional Dissipativity Approach for Data-Driven Safety Verification of Large-Scale Dynamical Systems

This work is concerned with a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">compositional data-driven approach</i> for formal safety verification of large-scale continuous-time dynamical systems with unknown models. The proposed framework enjoys the interconnection matrix and joint dissipativity-type properties of subsystems, described by the notion of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">stochastic storage certificates</i> . In the first part of the paper, we cast the required conditions for constructing storage certificates as a robust optimization program (ROP). Since the proposed ROP is not tractable due to the unknown model appearing in one of its constraints, we propose a scenario optimization program (SOP) corresponding to the original ROP by collecting finite numbers of data from trajectories of each subsystem. By establishing a probabilistic relation between the optimal value of SOP and that of ROP, we construct a storage certificate for each unknown subsystem based on the number of data and a required level of confidence. We accordingly propose a compositional technique based on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">dissipativity reasoning</i> to construct <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">stochastic barrier certificates</i> of interconnected systems based on storage certificates of individual subsystems. By leveraging the acquired barrier certificate, we quantify a lower bound on the probability that an interconnected system never reaches a certain unsafe region in finite time horizons with an a-priori guaranteed confidence. We also propose an auxiliary compositional approach without requiring any compositionality condition but at the cost of providing a potentially conservative safety guarantee. In the second part of the paper, we propose our approaches for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">deterministic</i> continuous-time systems with unknown dynamics. We verify our results over an unknown room temperature network containing 100 rooms.

Implementation of national whole-genome sequencing of Mycobacterium tuberculosis, National Public Health Laboratory, Singapore, 2019-2022.

The National Tuberculosis Programme (NTBP) monitors the occurrence and spread of tuberculosis (TB) and multidrug-resistant TB (MDR-TB) in Singapore. Since 2020, whole-genome sequencing (WGS) of Mycobacterium tuberculosis isolates has been performed at the National Public Health Laboratory (NPHL) for genomic surveillance, replacing spoligotyping and mycobacterial interspersed repetitive unit-variable number tandem repeats analysis (MIRU-VNTR). Four thousand three hundred and seven samples were sequenced from 2014 to January 2023, initially as research projects and later developed into a comprehensive public health surveillance programme. Currently, all newly diagnosed culture-positive cases of TB in Singapore are prospectively sent for WGS, which is used to perform lineage classification, predict drug resistance profiles and infer genetic relationships between TB isolates. This paper describes NPHL's operational and technical experiences with implementing the WGS service in an urban TB-endemic setting, focusing on cluster detection and genomic drug susceptibility testing (DST). Cluster detection: WGS has been used to guide contact tracing by detecting clusters and discovering unknown transmission networks. Examples have been clusters in a daycare centre, housing apartment blocks and a horse-racing betting centre. Genomic DST: genomic DST prediction (gDST) identifies mutations in core genes known to be associated with TB drug resistance catalogued in the TBProfiler drug resistance mutation database. Mutations are reported with confidence scores according to a standardized approach referencing NPHL's internal gDST confidence database, which is adapted from the World Health Organization (WHO) TB drug mutation catalogue. Phenotypic-genomic concordance was observed for the first-line drugs ranging from 2959/2998 (98.7 %) (ethambutol) to 2983/2996 (99.6 %) (rifampicin). Aspects of internal database management, reporting standards and caveats in results interpretation are discussed.

An adaptive classification and updating method for unknown network traffic in open environments

In recent years, to address the classification problem of unknown traffic in open network environments, numerous deep learning (DL)-based classification techniques have been proposed. Among these techniques, the single threshold-based DL method has gained significant popularity. However, the classification boundary constructed by this method is inaccurate, thus leading to the misclassification of known and unknown traffic. In this paper, we propose an adaptive classification and updating method for accurate application-level classification of known and unknown traffic in open environments. We adaptively construct individualized and accurate decision boundaries for each class of known traffic, which avoids misclassification cases caused by a single threshold and achieves accurate separation of known and unknown traffic. To provide a more accurate feature representation for the construction of the decision boundary, we also introduce an additional angular loss function to guide the model in learning more accurate flow features. In addition, to cope with the constant emergence of new classes of traffic in real network environments, our proposed method adaptively updates the model to respond to changes in network traffic classes. The proposed method is evaluated on two datasets, and the experimental results show that our proposed method has excellent classification accuracy and outperforms the state-of-the-art unknown traffic classification methods.

Noncooperative Topology Inference of Wireless Networks With Monitoring Sensors

With the widespread application of wireless networks, the importance of intelligent analysis of network behaviors is becoming increasingly prominent. In the analysis of networks behaviors, learning and reasoning about the connectivity of unknown networks is a fundamental problem. To obtain the topology information of a non-cooperative wireless network that could not be accessed by the monitoring sensors, we propose a topology inference algorithm based on the network two-dimensional spatio-temporal features (TDSTF). Specifically, the monitoring sensor network monitors the power of the non-cooperative network and locates the nodes of the non-cooperative network exploiting the neural network (NN)-based method. Then, the communication time and distance between the non-cooperative nodes are used as characteristics to infer the topology of the non-cooperative network based on K-Nearest Neighbors (KNN). Simulation results validate that the proposed TDSTF topology inference algorithm outperforms other topology inference algorithms that do not consider both spatial and temporal features and can greatly improve the inference accuracy.