Feb 2025· Scientific Reports· Vol 16· 1 citation· 47 references
MedicineComputer ScienceEngineering
TL;DR
A generalized Multimodal Subspace Support Vector Data Description model with graph-embedded regularization is proposed, illustrating how relational and structural information can be systematically embedded into one-class models, enabling robust learning under complex, high-dimensional, and multimodal conditions.
Abstract
Anomaly detection in smart power grids is a critical challenge due to the complexity, heterogeneity, and dynamic nature of sensor data streams. Existing one-class classification methods, particularly Subspace Support Vector Data Description (SVDD), have been extended to multimodal scenarios but often fail to fully exploit the structural dependencies across modalities, limiting their robustness in real-world applications. In this paper, we address this gap by proposing a generalized Multimodal Subspace Support Vector Data Description (MS-SVDD) model with graph-embedded regularization. The method projects data from multiple modalities into a shared low-dimensional subspace while preserving modality-specific structure through Laplacian regularizers. Our approach is evaluated on a three-modality dataset derived from smart grid event time series, using a dedicated preprocessing pipeline for constructing one-class classification training samples. The results demonstrate that our graph-embedded MS-SVDD improves robustness of event detection compared to conventional approaches, highlighting the potential of integrating graph priors with multimodal subspace learning for advancing anomaly detection in critical infrastructure. More broadly, this work contributes to the wider field of AI by illustrating how relational and structural information can be systematically embedded into one-class models, enabling robust learning under complex, high-dimensional, and multimodal conditions.
Unified anomaly detection requires modeling highly heterogeneous normal data without access to anomalous samples. While foundation models like DINOv2 provide rich token representations, leveraging these spaces for explicit density estimation remains challenging. Energy-Based Models (EBMs) offer a principled formulation, but their training in high-dimensional token spaces is unstable due to anisotropy and strong cross-dimensional correlations, which degrades finite-step Markov Chain Monte Carlo (MCMC) sampling. We identify this instability as fundamentally geometric and introduce ReFP-AD (Rectified Flow Preconditioning for Anomaly Detection), which learns a geometric reparameterization that maps high-dimensional embeddings into a well-conditioned latent space via an optimal transport (OT)-coupled rectified flow. This preconditioning enables stable persistent contrastive divergence with preconditioned Stochastic Gradient Langevin Dynamics (SGLD) in full-dimensional token spaces. Anomaly scores are then derived from the learned energy landscape using gradient norms. Under a strict unified protocol on the MVTec-AD and VisA datasets, ReFP-AD achieves 98.6%/97.9% Image/Pixel AUROC on MVTec-AD and 97.3%/99.0% on VisA, outperforming prior unified EBM baselines by up to +10.8% in Image AUROC. Ablation experiments demonstrate that geometric reparameterization is critical for finite-step MCMC and accurate anomaly localization in high-dimensional token spaces. Code is available at https://github.com/CLendering/ReFP-AD
Camile Lendering, Erkut Akdag, Joaquín Figueira et al.· 0 citations
The results indicate that entropy-based subgraph embedding can improve local anomaly detection performance, although the model does not achieve the best value for every metric on every dataset.
Gen Li, Jason J. Jung· Discover Computing· 0 citations
Multivariate Time Series Anomaly Detection (MTSAD) has multiple applications in real-world environments, e.g., vehicles, industrial plants, and monitoring systems. Most existing MTSAD approaches mainly focus on Transformer-based temporal modeling and representation-based learning, yet they still ignore two key limitations, i.e., sensitivity to noise perturbations and limited diversity of learned temporal representations, which hinder fine-grained discrimination between normal and anomalous samples. To address these issues, we introduce DAMR, a novel dual adaptive multi-head representation learning framework for the MTSAD task. Specifically, we design a feature extraction module based on the Multi-Scale Adaptive Spectral Block (MSASB) to capture multi-scale temporal patterns in both time and frequency domains. Then, we adopt multiple projection heads to generate diverse representations and capture variations induced by multiple data augmentations. Furthermore, to improve feature representation flexibility, we introduce an independent adaptive temperature for each projection head to re-weight similarity scores between time series pairs. Finally, extensive experiments and comparisons are conducted on five dominant datasets. The detailed experiments show that, compared with the current promising works, our DAMR achieves significant performance improvements and strong noise robustness, e.g., +5.7% on WADI, +4.7% on MSL. Notably, compared with Transformer-based temporal modeling works, our DAMR requires far less FLOPs and GPU memory cost. The code is available at https://github.com/wyn404/DAMR.
Yining Wang, Fujun Han, Ke Li et al.· Proceedings of the 32nd ACM...· 0 citations
The increasing complexity and scale of smart grids necessitate efficient and accurate real-time anomaly detection mechanisms to ensure grid reliability and security. Traditional detection methods often fall short in capturing the complex spatial and temporal dependencies inherent in smart grid data. This paper proposes a novel approach leveraging Graph Neural Networks (GNNs) to detect anomalies in smart grids by modeling the grid as a graph where nodes represent measurement points and edges represent electrical or communication connections. Our method exploits the graph structure and temporal dynamics to identify anomalies such as faults and cyber-attacks with high accuracy and low latency. Experimental evaluations on real and synthetic datasets demonstrate that the proposed GNN-based framework outperforms conventional machine learning models, offering a scalable and effective solution for real-time anomaly detection in smart grids.
Muhammad Al-Azar· International Journal of Art...· 0 citations
Microservice architecture is widely adopted in the digital transformation of smart grids, yet its distributed nature poses dual challenges for anomaly detection: the strong temporal periodicity of power grid data and the obscurity of fault propagation paths. This paper proposes a lightweight anomaly detection method integrating temporal-aware multimodal fusion and Graph Neural Network (GNN). Its core innovations are as follows: A lightweight temporal attention fusion strategy adaptive to power grid load periodicity, which enhances fusion accuracy without complex pre-training; A simplified GNN-based root cause localization method leveraging a compact power grid domain knowledge graph. Experiments on real power grid data demonstrate that the proposed method achieves an F1-score of 92.3% and a localization latency of 2.2 seconds, outperforming traditional methods by 2.5 - 3.0 percentage points in performance. Our research provides an efficient solution for the operation and maintenance of smart grid microservices.
Xin Liu, Boyan Tian, Jianfei Chen et al.· International Conference on...· 0 citations
Modern power grids are increasingly vulnerable to coordinated cyber-attacks, particularly false data injection attacks (FDIAs) that can evade conventional residual-based detectors. While most existing detection methods rely on instantaneous measurements, coordinated dynamic attacks can remain stealthy at each time step while introducing structured temporal deviations. This paper develops a joint framework for modeling and detecting such attacks in multi-area power systems. A time-aggregated attack model is first formulated to capture temporal evolution and inter-area coordination. For detection, a kernel-embedded functional subspace detection (KEFSD) method is proposed, which models residual trajectories in a reproducing kernel Hilbert space (RKHS) and employs RKHS-constrained functional principal component analysis (PCA) to identify anomalous temporal patterns. Simulation results on a modified IEEE 14-bus system demonstrates the proposed method achieves improved detection performance compared to the conventional residual based 2-norm detector.
Koto Omiloli, Satish Vedula, O. Anubi· 1 citation
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduAug 18, 2026
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
What does it take to trust AI-driven HVAC optimization? Our AI Model Factory combines agents, machine learning, reinforcement learning and deterministic checks in a governed workflow designed for messy, real-world building data. The post We built an AI factory for HVAC control appeared first on GPT-Lab.
MIT News · Artificial Intelligence· news.mit.eduJun 3, 2026
The new ChartNet training dataset could improve the accuracy of vision-language models that help analyze business trends or interpret scientific figures.
MIT News · Artificial Intelligence· news.mit.eduMay 20, 2026
