Most existing works in Industrial Internet of Things (IIoT) anomaly detection either depend on computationally intensive models that exceed the capabilities of multiaccess edge computing (MEC) servers, or lightweight models that lack robustness, making them unadaptable in IIoT infrastructures. To address these challenges, we propose THREADS , a hierarchical anomaly detection framework tailored for IIoT applications. The Instance thread utilizes an efficient variational auto encoder to produce instant feedback and offloads most of the workload to MECs. On the other hand, the Shadow thread employs an attention-enhanced transformer discriminator to examine low-confidence results in the cloud. Experimental results on five large-scale datasets show THREADS achieves an average F1-Score of 0.8537 in the hierarchical mode where most of the workloads are handled by MECs, and the random access memory and CPU usage is reduced by up to 29% and 88%, respectively. Meanwhile, THREADS achieves an F1-Score of 0.8563 in a cloud-based mode, consistently outperforming state-of-the-art approaches.

Industrial environments pose distinctive challenges for anomaly detection, primarily stemming from the complexities associated with high dimensionality and the dynamic nature of data patterns over time. These properties determine that the model’s proper convergence on unlabeled data is unpromising, consequently leading to less efficient discrimination of anomalies in previous anomaly detection (AD) works. To address this problem, we present AnoDual , a novel, meta-learning AD framework. From the perspective of data reconstruction, we introduce the multi-memory enhanced VAE reconstructor M2ER , which learns to extract the most salient patterns in unlabeled noisy data through a self-supervised manner. This design eases impacts from potential anomalous components during data reconstruction, and enhances the discernibility of anomalies. To address performance degradation caused by the numerical deviation based AD scheme in most existing works, we design a dual-source self-supervised discriminator DSD , which examines characteristics in the domain of representations. This model actively assesses discrepancies between data pairs and representation pairs in parallel, and conducts AD on a fine-grained scale. In this way, anomalies that used to be unnoticed due to a less prominent numerical deviation can be spotted. Besides, we propose a meta-learning powered training pipeline to enable model training even when no real label is available, which is common in the industry. Extensive experiments on five large-scale real-world industrial datasets suggest that AnoDual achieves an average F1-Score with a substantial increment of 3.39 %, outperforming the latest state-of-the-art baseline. Note to Practitioners —A generative model plus a numerical threshold based detection approach currently takes a significant share in both academia and the industry. However, the performance of this workflow is not promising in actual applications, with multiple factors contributing to this situation. The proper convergence of such generative models is difficult when the training material contains noisy samples -an over-expressed generative model would result in less significant reconstruction discrepancies for anomalies that are hard to notice. In addition, selecting a numerical threshold, which is used to spot anomalies, requires multiple laborious attempts, and can hardly adapt to an ever-changing pattern in industrial environments. These circumstances make it challenging to apply prior works in practical production, which, in turn, urges the need to develop an effective methodology to address the need for industrial anomaly detection. This manuscript includes a novel, meta-learning powered framework AnoDual , which is tailored for industrial scenarios. This framework discards the conventional design of comparing the reconstruction error numerically, but introduces a solution based on the differentiation of the representations. Besides, the multi-head attention enhanced variational autoencoder also leads to a much more pronounced discrepancy for anomalous samples, which benefits their successful detection. Providing a flexible and robust way to detect anomalies on deployed IoT assets, this work can be further transformed to serve applications in many other domains.

To identify pattern deviations in large-scale industrial infrastructures, anomaly detection is crucial yet challenging. Previous research has not adequately addressed the characteristics and deployment considerations in these complex scenarios. In this paper, we present InoU, a scalable anomaly detection framework to process unlabeled multivariate time-series data. We incorporate a VAE filter to ease impacts from noisy components in training materials. We propose a scalable trio-attention U-Transformer to construct the typical representation of high-dimensional streams and produce pseudo labels that enable the later training process. The ultra perception and intra-/ inter-flow attention mechanisms are delicately designed to aggregate information from different flows with variable granularities while keeping a global view of the data. Its nested structure helps to maintain high efficiency even when the model is scaled down. We introduce a Siamese discriminator that projects target data into manifolds, and collates discrepancies at the embedding level. This paradigm elevates detection performance far beyond segment- wise error comparison in prior works. We apply contrastive and adversarial learning techniques to optimize manifold projection and detection performance when processing unseen samples. Extensive experiments on five large-scale datasets demonstrate the effectiveness of InoU with an average F1-Score improvement of 5.58 %, significantly outperforming the state-of-the-art.

Graphic-pattern-based implicit authentication has been successfully exploited to elevate the security of smartphones. On-screen pressure is one of the key features in such an approach since it can reveal users’ touch pattern. However, state-of-the-art approaches rely on a system API to obtain on-screen pressure, which is not adequately accurate and cannot meet the demands of robust implicit authentication. To bridge this gap, we propose PresSafe, a novel implicit authentication system that utilizes the smartphone’s built-in barometer sensor to measure pressure during the unlocking process, and to utilize the pressure data in authentication. A key technical challenge in utilizing barometer sensing, however, is to understand the user activity through measured pressure. To overcome this challenge, PresSafe leverages barometer data along with data from other conventional but heterogeneous ambient sensors to produce accurate and robust user activity descriptions. PresSafe utilizes a transfer-learning-based hybrid workflow to integrate user activity representation learning with a lightweight classical authentication algorithm to obtain a unified model. This approach offloads the computational cost from the terminal and addresses privacy concerns. To ensure applicability of our approach despite data heterogeneity and insufficient training data, we utilize a channel-adaptive data processing mechanism. Extensive experiments utilizing more than 70000 records from 23 volunteers in six different locations show that PresSafe achieves an FAR of 0.45%, an FRR of 0.49%, and an EER of 0.47%, which clearly demonstrate its superiority over several existing solutions.

Air pollution has become a prominent problem in citizens’ everyday life. Since the weather stations are not densely distributed, it is difficult to get fine-grained particulate matter $< 2.5~\mu \text{m}$ (PM _2.5 ) data. We propose Meteorology Augmented Residual-Based Visual Approach for Crowdsourcing Air Quality Inference ( MARVAir ) to address limitations of traditional PM _2.5 prediction mechanism. First, we use crowdsourcing and spider-bots to fetch visual and meteorological dataset, respectively. Second, a residual neural network (ResNet)-based visual core is designed to learn the image data, and a 1-D convolutional neural network (CNN)-based meteorology core is deployed to tune the inference. Besides, we use decision-level fusion mechanism to unite the submodels and provide precise yet everywhere available fine-grained PM _2.5 inference. In addition, cloud-side model training is also proposed to restrict local energy consumption. Evaluation on dataset collected at eight sites over nearly two years suggests that MARVAir achieves a precision of 98.8%, a recall of 99.0%, and an $F1$ -score of 98.9% under various air conditions, which notably exceed baseline solutions.