Accelerated Local Anomaly Detection via Resolving Attributed Networks

We propose a novel unsupervised approach based on a two-stage object-centric adversarial framework that only needs object regions for detecting frame-level local anomalies in videos. The first stage consists in learning the correspondence between the current appearance and past gradient images of objects in scenes deemed normal, allowing us to either generate the past gradient from current appearance or the reverse. The second stage extracts the partial reconstruction errors between real and generated images (appearance and past gradient) with normal object behaviour, and trains a discriminator in an adversarial fashion. In inference mode, we employ the trained image generators with the adversarially learned binary classifier for outputting region-level anomaly detection scores. We tested our method on four public benchmarks, UMN, UCSD, Avenue and ShanghaiTech and our proposed object-centric adversarial approach yields competitive or even superior results compared to state-of-the-art methods.

<title>Abstract</title> Anomaly detection for time series data has been proven useful from both academia and industry, and can be categorized into global and local methodsbased on the range of data used to determine anomalies. To the best of our knowledge, there are no methods that unify the global and local methods together.In this study, we propose an approach that unifies the global and local anomaly detection to achieve the good performance. To make the unification possible, wediscretize time series data and partition the discrete data into global and local anomaly detection parts based on a concept of local factor. We design a rule-based global method using non-redundant association rules with tolerances to handle the difficulty of the latency phenomenon and the excessive number ofrules in time series data. We develop a Transformer based on local method with LSH (Locality Sensitive Hashing) Attention to fit better for discrete data. Wefinally conduct an extensive experimental study to verify the effectiveness and efficiency of our approach.

With recent advancements in field instrumentation technologies and the expansion of Saudi Aramco's state-of-the-art intelligent field infrastructure, a wealth of valuable knowledge is being derived from integrating intelligent field capabilities with best-in-class reservoir management practices. Intelligent field applications have already leveraged real-time reservoir surveillance data to enable timely responses and fast interventions for events observed from real-time data. As richer and more granular datasets are collected from the field, deeper insights and understanding of the reservoirs are gained at fractions of the needed time where intelligent field capabilities are not present. The abundance and timely processing of intelligent field data enables more tactical adjustments in reservoir management strategy. This type of real-time reservoir management has already shown great value in reservoir performance optimization. This paper discusses several cases in which an intelligent field enabled early detection of anomalies and shortened the time-cycle for an analysis, decision and action. The first case discusses the early detection of localized pressure support anomalies due to poor rock quality. This timely detection, facilitated by intelligent field infrastructure, enabled quick decision making and actions to overcome the anomaly. The second case shows how real-time monitoring of reservoir pressure propagation has helped to detect over-injection in two injectors with malfunctioned meters. This has allowed timely action to ensure uniform pressure propagation and repair of faulty equipment. The third case shows that the utilization of real-time data has assisted in detecting a casing leak in a short time, which helped in making a corrective action to restore the well's capacity. In all three cases, had an intelligent field not been there, the time-cycle from detection to analysis, and to decision and action, would have been substantially longer, resulting in higher operational costs and an impact on reservoir performance.

The article demonstrates the possibilities of using various types of unmanned aerial vehicles (UAVs) for geophysical research. UAVs are becoming a powerful tool for highspeed geophysical research in hard-to-reach areas for quick observation and measurements of certain parameters of physical fields. UAVs, capable of integrating geophysical sensors, become a powerful and effective tool for preparation of more detailed and more expensive geophysical observations of the Earth's physical fields for the study of the deep structure and detection of local anomalies. Obtaining spatial and geophysical data from unmanned aerial vehicles using sensors in combination with modern software and software modules allows to quickly and efficiently process data and obtain results of geophysical observations in the form of high-quality graphic material, point clouds, etc. in other specialized software

This paper investigates the potential contributions of traffic flow measurements in monitoring and network diagnostics. The basic idea is that information of diagnostic relevance may be obtained from the detection of local anomalies in a traffic trace. For this purpose, the paper introduces a novel approach in the analysis of aggregate traffic, which appears to be effective in evidencing potential flow anomalies

Anomaly detection is critical in industrial visual inspection, where undetected defects can lead to significant disruptions. While substantial progress has been made in detecting local anomalies such as scratches or dents, attention has recently shifted toward the more complex task of detecting logical anomalies, where visually normal components appear in semantically inconsistent configurations. To address this emerging task, we propose a novel model that resolves a key dilemma in Teacher–Student frameworks—namely, the risk of student over-generalization to anomalous inputs. Our approach introduces a reconstruction-based student network that learns to restore object-level semantics, such as type and quantity, enabling a more holistic understanding of normality beyond localized cues. Experiments demonstrate that the proposed method achieves balanced performance on both local and logical anomalies.

Traditional anomaly detection on social media mostly focuses on individual point anomalies while anomalous phenomena usually occur in groups. Therefore, it is valuable to study the collective behavior of individuals and detect group anomalies. Existing group anomaly detection approaches rely on the assumption that the groups are known, which can hardly be true in real world social media applications. In this article, we take a generative approach by proposing a hierarchical Bayes model: Group Latent Anomaly Detection (GLAD) model. GLAD takes both pairwise and point-wise data as input, automatically infers the groups and detects group anomalies simultaneously. To account for the dynamic properties of the social media data, we further generalize GLAD to its dynamic extension d-GLAD. We conduct extensive experiments to evaluate our models on both synthetic and real world datasets. The empirical results demonstrate that our approach is effective and robust in discovering latent groups and detecting group anomalies.

Smart Measurement Technique Employed for Detection of Localized Anomalies in the Atmosphere

Outlier detection is a key technique in data ming and machine learning fields. The deviating characters of outliers make huge detrimental effects on the learning tasks. A lot of algorithms are therefore proposed to handle outliers from different perspectives, such as distance, density, angle and so on. Among these approaches, the density-based methods achieve better performance, but also suffer from huge time complexity. Recently, in order to accelerate the speed and improve the performance, the subsampling ensemble method attracts much attention, which has a reasonable theoretical interpretation and high performance. However, existing work only gives the partial picture of outlier detection via row-sampling, the effective portfolio of bi-sampling is still void. In light of this, we propose the general outlier detection framework via bi-sampling, Bi-Sampling Outlier Detection (BSOD) and provide the effective portfolios of the row and column-sampling ratios in a theoretical way. In addition, the benefits of BSOD are fully illustrated in terms of ensemble diversity and divide-and-conquer. Further we employ LOF within BSOD as BI-LOF to conduct extensive experiments. In general, on 30 synthetic and 17 real-world data sets we thoroughly explore the characteristics of BI-LOF with different numbers of instances, features, nearest neighbors, validate the theoretical analysis of BSOD condition on synthetic data sets, and show obvious advantages over other state-of-the-art algorithms in terms of low and high dimensional real-world data sets. And finally we use BI-LOF to conduct image outlier detection and show high quality and stableness of BI-LOF.

Outlier detection shows its increasingly high practical value in many application areas such as intrusion detection, fraud detection, discovery of criminal activities in electronic commerce and so on. Many techniques have been developed for outlier detection, including distribution-based outlier detection algorithm, depth-based outlier detection algorithm, distance-based outlier detection algorithm, density-based outlier detection algorithm and clustering-based outlier detection. Spectral clustering receives much attention as a competitive clustering algorithms emerging in recent years. However, it is not very well scalable to modern large datasets. To partially circumvent this drawback, in this paper, we propose a new outlier detection method inspired by spectral clustering. Our algorithm combines the concept of kNN and spectral clustering techniques to obtain the abnormal data as outliers by using the information of eigenvalues and eigenvectors statistically in the feature space. We compare the performance of our methods with distance-based outlier detection methods and density-based outlier detection methods. Experimental results show the effectiveness of our algorithm for identifying outliers.

We propose an unsupervised method to detect lung lesions on FDG-PET/CT images based on deep image anomaly detection using 2.5-dimensional (2.5D) image processing. This 2.5D processing is applied to preprocessed FDG-PET/CT images without image patterns other than lung fields. It enhances lung lesions by parallel analysis of axial, coronal, and sagittal FDG-PET/CT slice images using multiple 2D U-Net. All the U-Nets are pretrained by 95 cases of normal FDG-PET/CT images having no lung lesions and used to transform CT slice images to normal FDG-PET slice images without any lesion-like SUV patterns. A lesion-enhanced image is obtained by merging subtractions of the transformed three normal FDG-PET images from the input FDG-PET image. Lesion detection is performed by simple binarization of the lesion-enhanced images. The threshold value varies from the case and is the 30-percentile voxel value of the target lesion-enhanced image. In each extracted region, the average of the intra-regional voxel values of the enhanced image is computed and assigned as a lesion-like score. We evaluated the proposed method by 27 patients FDG-PET/CT images with 41 lung lesions. The proposed method achieved 82.9 % of lesion detection sensitivity with five false positives per case. The result was significantly superior to the detection performance of FDG-PET image thresholding and indicates that the proposed method may be helpful for effective lung lesion detection. Future works include expanding the detectable range of lesions to outside lungs, such as mediastinum and axillae.

About Our Authors

We investigate the use of biased sampling according to the density of the data set to speed up the operation of general data mining tasks, such as clustering and outlier detection in large multidimensional data sets. In density-biased sampling, the probability that a given point will be included in the sample depends on the local density of the data set. We propose a general technique for density-biased sampling that can factor in user requirements to sample for properties of interest and can be tuned for specific data mining tasks. This allows great flexibility and improved accuracy of the results over simple random sampling. We describe our approach in detail, we analytically evaluate it, and show how it can be optimized for approximate clustering and outlier detection. Finally, we present a thorough experimental evaluation of the proposed method, applying density-biased sampling on real and synthetic data sets, and employing clustering and outlier detection algorithms, thus highlighting the utility of our approach.

Detecting anomalies in dynamic networks is essential for a range of real-world applications, such as social networks and cybersecurity. However, it encounters substantial challenges due to the diverse and ever-evolving nature of these anomalies. We present Attention-based Anomaly Detection In Dynamic Network (AADDN), an innovative end-to-end anomaly detection framework that utilizes attention mechanisms to capture the complex interactions between node attributes (individual characteristics) and structural features (collective patterns) across various time stamps. Unlike traditional methods that depend on heuristic rules with limited scope, AADDN employs a dual autoencoder architecture to learn comprehensive representations in the latent space, allowing the model to more effectively identify both individual and collective anomalies. By emphasizing the integrated learning of temporal, structural, and attribute information, our approach surpasses existing methods, showcasing superior anomaly detection capabilities in dynamic network environments.

In recent years, anomaly detection in web applications has become increasingly important for security and reliability. For instance, detecting fraudulent transactions in e-commerce platforms or monitoring user behavior in real-time web dashboards requires immediate response and high accuracy. Traditional deep learning models are difficult to deploy in browsers due to CPU/GPU bottlenecks, limited memory, and stringent real-time latency requirements. Deploying deep learning models directly in the browser is challenging due to limited computational resources and memory constraints. To address these challenges, we propose DAPQ-AD, a Dynamic-Aware Pruning-Quantization compression algorithm optimized for WebAssembly execution. Unlike conventional static compression methods, DAPQ-AD not only dynamically adjusts pruning rates and quantization levels based on the characteristics of the input data, but it also adapts to varying input noise, preserves critical features for accurate anomaly detection, and reduces inference latency compared to static approaches. Extensive experiments demonstrate that our method significantly reduces model size and inference latency while maintaining high anomaly detection performance in browser environments. This approach enables lightweight, real-time anomaly detection directly on client-side web applications without compromising accuracy.