Search Results (153)

Vehicle Ad hoc Networks (VANETs) play an essential role in intelligent transportation systems (ITSs) by improving road safety and traffic management through robust decentralized communication between vehicles and infrastructure. Yet, decentralization introduces security vulnerabilities, including spoofing, tampering, and denial-of-service attacks, which can compromise the reliability and safety of vehicular communications. Traditional centralized security mechanisms are often inadequate in providing the real-time response and scalability required by such dispersed networks. This research promotes a shift toward distributed and real-time technologies, including blockchain and secure multi-party computation, to enhance communication integrity and privacy, ultimately strengthening system resilience by eliminating single points of failure. A core aspect of this study is the novel D-CASBR framework, which integrates three essential components. First, it employs hybrid machine learning methods, such as ElasticNet and Gradient Boosting, to facilitate real-time anomaly detection, identifying unusual activities as they occur. Second, it utilizes a consortium blockchain to provide secure and transparent information exchange among authorized participants. Third, it implements a fog-enabled reputation system that uses distributed fog computing to effectively manage trust within the network. This comprehensive approach addresses latency issues found in conventional systems while significantly improving the reliability and efficacy of threat detection, achieving 95 percent anomaly detection accuracy with minimal false positives. The result is a substantial advancement in securing vehicular networks. Full article

Vehicular ad hoc networks (VANETs) enable communication among vehicles and between vehicles and infrastructure to provide safety and comfort to the users. Malicious nodes in VANETs may broadcast false information to create the impression of a fake event or road congestion. In addition, several malicious nodes may collude to collectively launch a false information attack to increase the credibility of the attack. Detection of these attacks is critical to mitigate the potential risks they bring to the safety of users. Existing techniques for detecting false information attacks in VANETs use different approaches such as machine learning, blockchain, trust scores, statistical methods, etc. These techniques rely on historical information about vehicles, artificial data used to train the technique, or coordination among vehicles. To address these limitations, we propose a false information attack detection technique for VANETs using an unsupervised anomaly detection approach. The objective of the proposed technique is to detect false information attacks based on only real-time characteristics of the network, achieving high accuracy and low processing delay. The performance evaluation results show that our proposed technique offers 30% lower data processing delay and a 17% lower false positive rate compared to existing approaches in scenarios with high proportions of malicious nodes. Full article

In industrial contexts, anomaly detection is crucial for ensuring quality control and maintaining operational efficiency in manufacturing processes. Leveraging high-level features extracted from ImageNet-trained networks and the robust capabilities of the Deep Support Vector Data Description (SVDD) model for anomaly detection, this paper proposes an improved Deep SVDD model, termed Feature-Patching SVDD (FPSVDD), designed for unsupervised anomaly detection in industrial applications. This model integrates a feature-patching technique with the Deep SVDD framework. Features are extracted from a pre-trained backbone network on ImageNet, and each extracted feature is split into multiple small patches of appropriate size. This approach effectively captures both macro-structural information and fine-grained local information from the extracted features, enhancing the model’s sensitivity to anomalies. The feature patches are then aggregated and concatenated for further training with the Deep SVDD model. Experimental results on both the MvTec AD and CIFAR-10 datasets demonstrate that our model outperforms current mainstream approaches and provides significant improvements in anomaly detection performance, which is vital for industrial quality assurance and defect detection in real-time manufacturing scenarios. Full article

Anomaly detection is critical in safety-sensitive fields, but faces challenges from scarce abnormal data and costly expert labeling. Time series anomaly detection is relatively challenging due to its reliance on sequential data, which imposes high computational and memory costs. In particular, it is often composed of real-time collected data that tends to be noisy, making preprocessing an essential step. In contrast, image anomaly detection has leveraged advancements in technologies for analyzing spatial patterns and visual features, achieving high accuracy and promoting research aimed at improving efficiency. We propose a novel framework that bridges image anomaly detection with time series data. Using Gramian Angular Field (GAF) transformations, we convert time series into images and apply state-of-the-art techniques, Reverse Distillation (RD) and EfficientAD (EAD), for efficient and accurate anomaly detection. Tailored preprocessing and transformations further enhance performance and interoperability. When evaluated on the multivariate time series anomaly detection dataset Secure Water Treatment (SWaT) and the univariate datasets University of California, Riverside (UCR) and Numenta Anomaly Benchmark (NAB), our approach demonstrated high recall overall and achieved approximately 99% F1 scores on some univariate datasets, proving its effectiveness as a novel solution for time series anomaly detection. Full article

We focus on detecting anomalies in images where the data distribution is supported by a lower-dimensional embedded manifold. Approaches based on autoencoders have aimed to control their capacity either by reducing the size of the bottleneck layer or by imposing sparsity constraints on their activations. However, none of these techniques explicitly penalize the reconstruction of anomalous regions, often resulting in poor detection. We tackle this problem by adapting a self-supervised learning regime that essentially implements a denoising autoencoder with structured non-i.i.d. noise. Informally, our objective is to regularize the model to produce locally consistent reconstructions while replacing irregularities by acting as a filter that removes anomalous patterns. Formally, we show that the resulting model resembles a nonlinear orthogonal projection of partially corrupted images onto the submanifold of uncorrupted examples. Furthermore, we identify the orthogonal projection as an optimal solution for a specific regularized autoencoder related to contractive and denoising variants. In addition, orthogonal projection provides a conservation effect by largely preserving the original content of its arguments. Together, these properties facilitate an accurate detection and localization of anomalous regions by means of the reconstruction error. We support our theoretical analysis by achieving state-of-the-art results (image/pixel-level AUROC of 99.8/99.2%) on the MVTec AD dataset—a challenging benchmark for anomaly detection in the manufacturing domain. Full article

Multivariate time series anomaly detection is a crucial technology to prevent unexpected errors from causing critical impacts. Effective anomaly detection in such data requires accurately capturing temporal patterns and ensuring the availability of adequate data. This study proposes a patch-wise framework for anomaly detection. The proposed approach comprises four key components: (i) maintaining continuous features through patching, (ii) incorporating various temporal information by learning channel dependencies and adding relative positional bias, (iii) achieving feature representation learning through self-supervised learning, and (iv) supervised learning based on anomaly augmentation for downstream tasks. The proposed method demonstrates strong anomaly detection performance by leveraging patching to maintain temporal continuity while effectively learning data representations and handling downstream tasks. Additionally, it mitigates the issue of insufficient anomaly data by supporting the learning of diverse types of anomalies. The experimental results show that our model achieved a 23% to 205% improvement in the F1 score compared to existing methods on datasets such as MSL, which has a relatively small amount of training data. Furthermore, the model also delivered a competitive performance on the SMAP dataset. By systematically learning both local and global dependencies, the proposed method strikes an effective balance between feature representation and anomaly detection accuracy, making it a valuable tool for real-world multivariate time series applications. Full article

Global population aging creates distinct healthcare needs, particularly for older adults and those with serious illnesses. There are several gaps in current models for monitoring elderly individuals. These include the limited application of advanced deep learning techniques in elderly health monitoring, the lack of real-time anomaly detection for vital signs, the absence of robust evaluations using real-world data, and the failure to tailor monitoring systems specifically for the unique needs of elderly individuals. This study addresses these gaps by proposing a Hierarchical Attention-based Temporal Convolutional Network (HATCN) model, which enhances anomaly detection accuracy and validates effectiveness using real-world datasets. While the HATCN approach has been used in other fields, it has not yet been applied to elderly healthcare monitoring, making this contribution novel. Specifically, this study introduces a Hierarchical Attention-based Temporal Convolutional Network with Anomaly Detection (HATCN-AD) model, based on the real-world MIMIC-II dataset. The model was validated using two subjects from the MIMIC-II dataset: Subject 330 (Dataset 1) and Subject 441 (Dataset 2). For Dataset 1 (Subject 330), the model achieved an accuracy of 99.15% and precision of 99.47%, with stable recall (99.45%) and F1-score (99.46%). Similarly, for Dataset 2 (Subject 441), the model achieved 99.11% accuracy, 99.35% precision, and an F1-score of 99.44% at 100 epochs. The results show that the HATCN-AD model outperformed similar models, achieving high recall and precision with low false positives and negatives. This ensures accurate anomaly detection for real-time healthcare monitoring. By combining Temporal Convolutional Networks and attention mechanisms, the HATCN-AD model effectively monitors elderly patients’ vital signs. Full article

Multi-class anomaly detection is more efficient and less resource-consuming in industrial anomaly detection scenes that involve multiple categories or exhibit large intra-class diversity. However, most industrial image anomaly detection methods are developed for one-class anomaly detection, which typically suffer significant performance drops in multi-class scenarios. Research specifically targeting multi-class anomaly detection remains relatively limited. In this work, we propose a powerful unified normalizing flow for multi-class anomaly detection, which we call UniFlow. A multi-cognitive visual adapter (Mona) is employed in our method as the feature adaptation layer to adapt image features for both the multi-class anomaly detection task and the normalizing flow model, facilitating the learning of general knowledge of normal images across multiple categories. We adopt multi-cognitive convolutional networks with high capacity to construct the coupling layers within the normalizing flow model for more effective multi-class distribution modeling. In addition, we employ a multi-scale feature fusion module to aggregate features from various levels, thereby obtaining fused features with enhanced expressive capabilities. UniFlow achieves a class-average image-level AUROC of 99.1% and a class-average pixel-level AUROC of 98.0% on MVTec AD, outperforming the SOTA multi-class anomaly detection methods. Extensive experiments on three benchmark datasets, MVTec AD, VisA, and BTAD, demonstrate the efficacy and superiority of our unified normalizing flow in multi-class anomaly detection. Full article

Anomaly detection is crucial in large-scale industrial manufacturing as it helps to detect and localize defective parts. Pre-training feature extractors on large-scale datasets is a popular approach for this task. Stringent data security, privacy regulations, high costs, and long acquisition time hinder the development of large-scale datasets for training and benchmarking. Despite recent work focusing primarily on the development of new anomaly detection methods based on such extractors, not much attention has been paid to the importance of the data used for pre-training. This study compares representative models pre-trained with fractal images against those pre-trained with ImageNet, without subsequent task-specific fine-tuning. We evaluated the performance of eleven state-of-the-art methods on MVTecAD, MVTec LOCO AD, and VisA, well-known benchmark datasets inspired by real-world industrial inspection scenarios. Further, we propose a novel method to create a dataset by combining the dynamically generated fractal images creating a “Multi-Formula” dataset. Even though pre-training with ImageNet leads to better results, fractals can achieve close performance to ImageNet under proper parametrization. This opens up the possibility for a new research direction where feature extractors could be trained on synthetically generated abstract datasets mitigating the ever-increasing demand for data in machine learning while circumventing privacy and security concerns. Full article

Production efficiency is used to determine the best conditions for manufacturing goods at the lowest possible unit cost. When achieved, production efficiency leads to increased revenues for the manufacturer, enhanced employee safety, and a satisfied customer base. Production efficiency not only measures the amount of resources that are needed for production but also considers the productivity levels and the state of the production lines. In this context, online anomaly detection (AD) is an important tool for maintaining the reliability of the production ecosystem. With advancements in artificial intelligence and the growing significance of identifying and mitigating anomalies across different fields, approaches based on artificial neural networks facilitate the recognition of intricate types of anomalies by taking into account both temporal and contextual attributes. In this paper, a lightweight framework based on the Echo State Network (ESN) model running at the edge is introduced for online AD. Compared to other AD methods, such as Long Short-Term Memory (LSTM), it achieves superior precision, accuracy, and recall metrics while reducing training time, CO₂ emissions, and the need for high computational resources. The preliminary evaluation of the proposed solution was conducted using a low-resource computing device at the edge of the real production machine through an Industrial Internet of Things (IIoT) smart meter module. The machine used to test the proposed solution was provided by the Italian company SIFIM Srl, which manufactures filter mats for industrial kitchens. Experimental results demonstrate the feasibility of developing an AD method that achieves high accuracy, with the ESN-based framework reaching $85\%$ compared to $80.88\%$ for the LSTM-based model. Furthermore, this method requires minimal hardware resources, with a training time of $9.5$ s compared to $2.100$ s for the other model. Full article

Optimizing energy consumption is an important aspect of industrial competitiveness, as it directly impacts operational efficiency, cost reduction, and sustainability goals. In this context, anomaly detection (AD) becomes a valuable methodology, as it supports maintenance activities in the manufacturing sector, allowing for early intervention to prevent energy waste and maintain optimal performance. Here, an AD-based method is proposed and studied to support energy-saving predictive maintenance of production lines using time series acquired directly from the field. This paper proposes a deep echo state network (DeepESN)-based method for anomaly detection by analyzing energy consumption data sets from production lines. Compared with traditional prediction methods, such as recurrent neural networks with long short-term memory (LSTM), although both models show similar time series trends, the DeepESN-based method studied here appears to have some advantages, such as timelier error detection and higher prediction accuracy. In addition, the DeepESN-based method has been shown to be more accurate in predicting the occurrence of failure. The proposed solution has been extensively tested in a real-world pilot case consisting of an automated metal filter production line equipped with industrial smart meters to acquire energy data during production phases; the time series, composed of 88 variables associated with energy parameters, was then processed using the techniques introduced earlier. The results show that our method enables earlier error detection and achieves higher prediction accuracy when running on an edge device. Full article

While the massive adoption of Artificial Intelligence (AI) is threatening the environment, new research efforts begin to be employed to measure and mitigate the carbon footprint of both training and inference phases. In this domain, two carbon-aware training strategies have been proposed in the literature: Flexible Start and Pause & Resume. Such strategies—natively Cloud-based—use the time resource to postpone or pause the training algorithm when the carbon intensity reaches a threshold. While such strategies have proved to achieve interesting results on a benchmark of modern models covering Natural Language Processing (NLP) and computer vision applications and a wide range of model sizes (up to 6.1B parameters), it is still unclear whether such results may hold also with different algorithms and in different geographical regions. In this confirmation study, we use the same methodology as the state-of-the-art strategies to recompute the saving in carbon emissions of Flexible Start and Pause & Resume in the Anomaly Detection (AD) domain. Results confirm their effectiveness in two specific conditions, but the percentage reduction behaves differently compared with what is stated in the existing literature. Full article

Mobile ad hoc networks (MANETs) have revolutionized wireless communications by enabling dynamic, infrastructure-free connectivity across various applications, from disaster recovery to military operations. However, these networks are highly vulnerable to security threats, particularly black hole and gray hole attacks, which can severely disrupt network performance and reliability. This study addresses the critical challenge of detecting and mitigating these attacks within the framework of the dynamic source routing (DSR) protocol. To tackle this issue, we propose a robust hybrid detection method that significantly enhances the identification and mitigation of black hole and gray hole attacks. Our approach integrates anomaly detection, advanced data mining techniques, and cryptographic verification to establish a multi-layered defense mechanism. Extensive simulations demonstrate that the proposed hybrid method achieves superior detection accuracy, reduces false positives, and maintains high packet delivery ratios even under attack conditions. Compared to existing solutions, this method provides more reliable and resilient network performance, dynamically adapting to evolving threats. This research represents a significant advancement in MANET security, offering a scalable and effective solution for safeguarding critical MANET applications against sophisticated cyber-attacks. Full article

The increasing reliance of Vehicular Ad-hoc Networks (VANETs) on the BeiDou Navigation Satellite System (BDS) for precise positioning and timing information has raised significant concerns regarding their vulnerability to spoofing attacks. This research proposes a novel approach to mitigate BeiDou spoofing attacks in VANETs by leveraging a hybrid machine learning model that combines XGBoost and Random Forest with a Kalman Filter for real-time anomaly detection in BeiDou signals. It also introduces a geospatial message authentication mechanism to enhance vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication security. The research investigates low-cost and accessible countermeasures against spoofing attacks using COTS receivers and open-source SDRs. Spoofing attack scenarios are implemented in both software and hardware domains using an open-source BeiDou signal simulator to examine the effects of different spoofing attacks on victim receivers and identify detection methods for each type, focusing on pre-correlation techniques with power-related metrics and signal quality monitoring using correlator values. The emulation results demonstrate the effectiveness of the proposed approach in detecting and mitigating BeiDou spoofing attacks in VANETs, ensuring the integrity and reliability of safety-critical information. This research contributes to the development of robust security mechanisms for VANETs and has practical implications for enhancing the resilience of transportation systems against spoofing threats. Future research will focus on extending the proposed approach to other GNSS constellations and exploring the integration of additional security measures to further strengthen VANET security. Full article

Anomaly detection has gained significant attention with the advancements in deep neural networks. Effective training requires both normal and anomalous data, but this often leads to a class imbalance, as anomalous data is scarce. Traditional augmentation methods struggle to maintain the correlation between anomalous patterns and their surroundings. To address this, we propose an adjacent augmentation technique that generates synthetic anomaly images, preserving object shapes while distorting contours to enhance correlation. Experimental results show that adjacent augmentation captures high-quality anomaly features, achieving superior AU-ROC and AU-PR scores compared to existing methods. Additionally, our technique produces synthetic normal images, aiding in learning detailed normal data features and reducing sensitivity to minor variations. Our framework considers all training images within a batch as positive pairs, pairing them with synthetic normal images as positive pairs and with synthetic anomaly images as negative pairs. This compensates for the lack of anomalous features and effectively distinguishes between normal and anomalous features, mitigating class imbalance. Using the ResNet50 network, our model achieved perfect AU-ROC and AU-PR scores of 100% in the bottle category of the MVTec-AD dataset. We are also investigating the relationship between anomalous pattern size and detection performance. Full article