90 articles tagged with #anomaly-detection. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers introduce CATCH, a novel framework for detecting anomalies in multivariate time series data using frequency patching and channel-aware mechanisms. The method achieves state-of-the-art performance across 22 datasets by improving detection of fine-grained frequency patterns while identifying relevant channel correlations through a Channel Fusion Module.
Researchers developed an LSTM-based machine learning system to identify IoT devices using network packet analysis, achieving 79.85% accuracy across 27 device classes. This work addresses growing security vulnerabilities in IoT deployments by enabling automated device recognition and vulnerability detection.
Researchers propose a novel unsupervised anomaly detection method that directly couples representation learning with One-Class SVM through a custom loss function, addressing limitations in existing reconstruction-based and decoupled approaches. The method demonstrates effectiveness on image corruption benchmarks and clinical brain MRI lesion detection, showing robustness to domain shifts without requiring labeled anomalous data.
Researchers have developed an LLM-driven framework to generate synthetic human trajectory anomalies with kinematic constraints, addressing the critical shortage of ground-truth anomaly datasets in spatial data mining. The system combines large language models with map-constrained routing and context-aware noise modeling to create realistic, annotated mobility anomalies at scale while respecting physical constraints.
A research thesis addresses critical limitations in automated anomaly detection and root cause analysis (RCA) for microservice systems by introducing integrated methods that leverage multiple data types and establishing standardized benchmarking frameworks. The work combines anomaly detection with RCA, incorporates event data alongside traditional metrics, and eliminates dependency on service call graphs while advancing causal inference techniques.
Researchers propose a novel framework for detecting Advanced Persistent Threats (APTs) across different operating systems without labeled target data, using semantic embeddings and Optimal Transport theory. The source-only approach combines language models, graph autoencoders, and transport-based anomaly scoring to identify malicious processes in cross-OS environments, demonstrating improved detection performance across Linux, Windows, BSD, and Android platforms.
Researchers have developed a multi-similarity Siamese neural network that detects and classifies zero-day anomalies in optical networks with over 99% accuracy, requiring no retraining when deployed across different network paths or encountering previously unseen anomaly types. This advancement addresses a critical gap in network security by enabling instant adaptability to emerging threats without manual intervention.
Researchers have developed an AI-powered security agent for university academic management systems that detects multi-vector threats through anomaly detection and behavioral analytics, achieving 91% F1 detection accuracy compared to 49% for traditional rule-based systems, with response latency under 300ms.
Researchers introduce a novel anomaly detection framework combining visual prompting, unfrozen teacher models, and diffusion-based data augmentation to address real-world limitations in industrial inspection systems. The approach achieves a 3.5 percentage point improvement on the challenging AeBAD dataset, demonstrating practical applicability beyond controlled laboratory conditions.
Researchers introduce IDS-Anta++, an enhanced machine learning framework that defends intrusion detection systems against adversarial attacks through ensemble learning and multi-layer defensive mechanisms. The system achieves over 99% detection accuracy on clean data while demonstrating improved robustness against sophisticated attacks like FGSM and ZOO on standard cybersecurity datasets.
Researchers introduce XAInomaly, an explainable AI framework using a Semi-supervised Deep Contractive Autoencoder for detecting anomalies in Open RAN (O-RAN) networks. The system addresses the critical need for interpretable machine learning in complex wireless infrastructure by combining generative modeling with explainability techniques to identify network traffic deviations while maintaining transparency in decision-making.
Researchers introduce GITCO, a lightweight inference-time optimization framework that improves Time Series Foundation Models (TSFMs) by identifying and suppressing anomalous patches without modifying model weights. The method achieves a 1.95% average improvement in forecast accuracy on TimesFM 2.5, addressing the critical problem of context poisoning where structurally irregular data segments degrade zero-shot prediction quality.
Researchers present DAST, a zero-shot AI framework combining Vision Language Models and Large Language Models to detect anomalies and denial-of-service attacks in O-RAN (Open Radio Access Network) infrastructure. The system achieved 0.910 F1-Score by converting network telemetry into visual representations and cross-referencing them against domain knowledge, addressing critical security gaps in disaggregated 5G/6G networks.
Researchers propose DMAIC-IAD, an LLM-based multi-agent system for industrial anomaly detection that combines structured planning with pre-trained judgment models. The system achieves 37.76% performance improvement over existing agentic baselines by standardizing heterogeneous data inputs and evaluating strategies without costly runtime execution.
Researchers introduce TPA-AD, a two-stage machine learning method for detecting anomalies in bearing time-series data using only normal training samples. The approach generates synthetic anomalies near normal boundaries and uses contrastive learning to identify degradation patterns, demonstrating improved performance on bearing fault detection and broader applicability across 13 public anomaly detection datasets.
Researchers introduced AnomSeer, a system that enhances multimodal large language models for time-series anomaly detection by grounding reasoning in precise structural details rather than coarse heuristics. Using a novel reinforcement learning approach called TimerPO, AnomSeer outperforms larger commercial models like GPT-4o in classification and localization accuracy while providing interpretable reasoning traces.
Researchers propose a novel framework for detecting anomalies in dynamic graphs using limited labeled data, combining residual representation encoding with a bi-boundary optimization strategy to balance discrimination and generalization. The model-agnostic approach addresses the gap between unsupervised methods (which produce ambiguous boundaries) and semi-supervised methods (which overfit to limited anomalies).
Researchers introduce a Privacy Policy Enforcement framework that detects subtle data leakage in RAG systems beyond standard PII filters, using dual one-class density estimators to identify contextual attribute clusters that collectively identify individuals. The T3+OCSVM detector achieves 93%+ AUROC while reducing false positives by 44-55% and maintaining millisecond latency, outperforming traditional supervised approaches.
Researchers propose Product-Aware Deep Autoencoders to improve anomaly detection in multi-product manufacturing environments, addressing a critical vulnerability where traditional global models fail to detect cyber-physical attacks. Testing on the Tennessee Eastman Process benchmark demonstrates the approach achieves 100% detection accuracy versus 22.2% for conventional models under attack scenarios.
Researchers address critical class imbalance problems in IoT intrusion detection by applying SMOTE oversampling to power-based side-channel datasets, achieving superior detection performance with Random Forest and Extra Trees algorithms. The study demonstrates that balanced datasets reveal minority attack classes previously missed by traditional evaluation metrics, advancing security for IoT networks.
Researchers propose Score-Guided Classification (SGC), a novel machine learning framework for detecting Major Depressive Disorder from EEG signals that bypasses traditional data augmentation by using anomaly scoring to guide classification without synthesizing additional data. The method achieves strong results on multiple datasets while reducing computational overhead and maintaining generalizability across different hardware configurations.
DarkVesselNet is a multi-modal AI system that detects unregistered vessels by combining satellite radar and optical imagery with AIS trajectory data and anomaly detection algorithms. The open-source framework addresses maritime surveillance challenges and is available as both a Python package and public Hugging Face interface.
Researchers present a machine-vision system design for real-time carpet quality control that combines automated defect detection with systematic data collection for training AI models. The proposal, grounded in an actual Six Sigma manufacturing project, addresses production bottlenecks by moving beyond slow manual inspection to progressively improve defect detection through a staged machine-learning approach.
Researchers propose a hybrid machine learning framework combining data-level and algorithm-level balancing techniques to address imbalanced regression problems, where underrepresented target values typically degrade model performance. The framework integrates adaptive partitioning, conditional variational autoencoders, strategic oversampling, and a novel weighted loss function to improve predictions on rare but important cases.
ChronosAD introduces a foundation-model-based approach to time series anomaly detection that combines zero-shot embeddings with a custom Temporal Block architecture. The method achieves 4.72% improvement in AUC and 6.60% in AP across 11 benchmarks while requiring minimal task-specific tuning, enabling robust generalization across finance, healthcare, and industrial domains.
