Latest Anomaly Detection Research Papers
The newest Anomaly Detection papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Anomaly Detection so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.
Get the latest Anomaly Detection papers in your inbox — free →Recent papers
- Construction of an Automated Quality Control Model for Industrial Waste Gas Online Monitoring Data Based on Unsupervised LearningTao Lin · Knowledge Commons (Lakehead... · Dec 31, 2026
Continuous Emission Monitoring Systems (CEMS) for stationary pollution sources serve as the core data backbone for precision pollution control and environmental law enforcement. However, traditional data quality control (QC) primarily relie…
- Construction of an Automated Quality Control Model for Industrial Waste Gas Online Monitoring Data Based on Unsupervised LearningTao Lin · PhilPapers (PhilPapers Foun... · Dec 31, 2026
Continuous Emission Monitoring Systems (CEMS) for stationary pollution sources serve as the core data backbone for precision pollution control and environmental law enforcement. However, traditional data quality control (QC) primarily relie…
- Continuous Auditing: AI systems that monitor transactions in real timePrakash Chandan, Krishna Chaithanya · Zenodo (CERN European Organ... · Oct 31, 2026
Abstract The rapid advancement of Artificial Intelligence (AI) has transformed the auditing profession by enabling continuous auditing systems capable of monitoring financial transactions in real time. Unlike traditional auditing methods, w…
- Rethinking Neural Thickets Without Weight PerturbationsNicolas Dufour, Elouan Gardès, Amil Dravid, Patrick Pérez et al. · arXiv · Oct 29, 2026
The Neural Thickets hypothesis posits that pretrained language models lie in dense neighborhoods of task-specific experts in weight space, which random Gaussian perturbations can uncover. We reproduce the reported gains, but show that they …
- Training Foundation Models with a Single AlgorithmYuda Song, Alvin Zhang, Fahim Tajwar, Daman Arora et al. · arXiv · Oct 29, 2026
Foundation models are typically trained in stages: pretraining, midtraining, supervised fine-tuning (SFT), and reinforcement learning (RL), with changes in both data and learning algorithms. We show that this algorithmic separation is not f…
- Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for PortuguesePedro Carvalho Brom · arXiv · Oct 29, 2026
Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell whether it is good for the tasks of a specialist domain. It propo…
- Does System Size Matter in Uncertainty Quantification for Machine Learning Interatomic Potentials?Chayaphol Lortaraprasert, Nontawat Charoenphakdee, Wenwen Li, Yong-Bin Zhuang et al. · arXiv · Oct 29, 2026
Machine-learning interatomic potentials (MLIPs) commonly use uncertainty estimates to flag out-of-distribution (OOD) configurations and select structures for active learning. A key question is whether the resulting structure-level uncertain…
- Context-Aware Longitudinal Patient Health Intelligence for Personalized Early Detection of Health AnomaliesHye-Seen Kang · Asia-pacific Journal of Con... · Oct 29, 2026
- Graph Representation Learning via Adaptive Expectile AggregationTianyi Zhu, Wei Lan · arXiv · Oct 27, 2026
Graph neural networks (GNNs) rely critically on neighborhood aggregation, yet conventional mean aggregation may fail to capture class-relevant distributional information, particularly in heterophilic graphs. We propose ExpectileGCN, an adap…
- Smart Home Anomaly Detection using K-Means Dynamic Threshold and Isolation Forest based on Multi-Sensor DataHyungsuk Lee, Haneum Lee, In-Nea Wang, Junho Jeong · Journal of Korean institute... · Oct 27, 2026
- Retrocaval Ureter Diagnosed Following Point-of-Care Ultrasound Detection of Hydronephrosis: A Case ReportNoah Marzook, Mostafa Alhabboubi, Ahmad Koshak, Abdullah Mohammed Basnawi et al. · Clinical Practice and Cases... · Oct 27, 2026
Introduction: Retrocaval ureter (RCU) is a rare congenital anomaly resulting from abnormal development of the inferior vena cava, leading to ureteral obstruction and hydronephrosis. Patients often present with nonspecific symptoms, making d…
- A theory of noisy linear recurrent neural network learning dynamicsJohn J. Vastola, Kanaka Rajan · arXiv · Oct 26, 2026
Biological neural networks are noisy: their dynamics involve difficult-to-predict fluctuations which are likely due not just to chaos, but also to a variety of low-level biophysical processes. Despite the omnipresence of intrinsic noise, it…
- Detecting bus delays and service anomalies in Niterói with autoencoder latent feature representationsMatheus Germano, Claudio E. C. Campelo · arXiv · Oct 26, 2026
Bus riders judge service by two failures: single trips that run late, and days on which the whole system misbehaves. We ask whether one unsupervised representation of raw GPS telemetry can serve both diagnoses on the NetMob 2026 Niterói bus…
- ExCal: Optimization-Free Multivariate Time Series Anomaly Detection via Excess CalibrationKadir-Kaan Özer, René Ebeling, Markus Enzweiler · arXiv · Oct 26, 2026
We introduce ExCal, a normal-only multivariate time series anomaly detector that combines raw state retrieval, a signal/derivative subspace, and robust statistics across temporal scales. Each expert map receives a high normality floor from …
- Loss of PAX6 alters the excitatory/inhibitory neuronal ratio in human cerebral organoidsWai Kit Chan, Shibla Abdulla, Lusi Zhao, Danilo Negro et al. · Development · Oct 26, 2026
The transcription factor PAX6 is a crucial regulator of multiple aspects of embryonic forebrain development. It has well-established roles in the regulation of excitatory and inhibitory neuron development in the embryonic cortex in mice but…
- A Theoretical Framework for Anomaly Detection in Astrophysical Data Using K-DTC and the Kalimuthu Calcmanifold Approach: A Conceptual Contribution to SETI and Anomaly ScienceKalimuthu Sennimalai · Zenodo (CERN European Organ... · Oct 25, 2026
- Multi-scale LSTM forecasting with attention-based feature fusion for anomaly detection in multivariate monitoring dataWei Liu, Meizhao Liu, Fei Xia, Zhong Qiuyuan et al. · Journal of Engineering and ... · Oct 24, 2026
Abstract Engineering systems such as power equipment and industrial processes are monitored through multivariate time series whose anomalies appear at different temporal scales, from short fluctuations to deviations that persist over a whol…
- Artificial Intelligence in Next-Generation Firewalls for Discriminating Cyber Attacks from Legitimate Service Traffic SurgesSamir Khanji · International Journal of In... · Oct 24, 2026
Next-generation firewalls (NGFWs) sit on the critical path between public networks and production services. Their most consequential error is no longer a missed signature; it is the inability to tell a malicious flood from a genuine surge i…
- Flownomaly: Single-Step Conditional-Mean Recovery for Few-Shot Anomaly DetectionBernardo Perrone Ribeiro, Erkut Akdag, Egor Bondarev · arXiv · Oct 23, 2026
Few-shot industrial anomaly detection requires modeling category-specific normality from only a handful of defect-free images. Common approaches tie inference to stored exemplars, impose rigid linear structure, or risk reproducing anomalous…
- Multiplicative vs. Additive State Coupling in Learned Optimizer SchedulesM. Harper Langston, Pierre-David Letourneau, Dalton Jones, Roland Memisevic et al. · NeurIPS · Oct 23, 2026
We learn schedules for a continuous penalty relaxation of MAX-CUT by backpropagating through an unrolled classical solver. A state-blind schedule generalizes to instances substantially larger than those used for training. A state-adaptive b…
- Clean-label Poisoning Attack and Defense Game for Federated Learning in Vehicular NetworksYalin E. Sagduyu, Tugba Erpek, Nathan Stephenson, Mengran Xue · arXiv · Oct 23, 2026
This paper studies interactions between clean-label poisoning attack and defense in vehicular networks using federated learning (FL). Basic Safety Message (BSM) classification for anomaly detection is modeled as a distributed learning probl…
- Efficient Zero-Shot Video Anomaly Detection via Signal-Aware Adaptive Fusion (SAAF)Khaled Waleed Dawoud, Muhammad Haris Khan · arXiv · Oct 23, 2026
Deploying Vision-Language Models for video anomaly detection confronts a fundamental constraint. Their semantic reasoning demands computational budgets incompatible with the scale of real-world video streams. We present Signal-Aware Adaptiv…
- Online Continual Learning in Edge-Cloud ApplicationsCharalampos Davalas, Dimitrios Michail, Christos Diou, Iraklis Varlamis et al. · arXiv · Oct 23, 2026
Deployed machine learning models in real-world IoT and edge/cloud systems face a critical reliability bottleneck: the requirement for online adaptation to non-stationary data streams while operating without access to the full original train…
- Data Quality Audit and Bivariate Temperature-Humidity Analysis of a Long-Term LoRaWAN Network: Anomaly Detection, PCA, Clustering and Machine LearningMamadou Sow · arXiv · Oct 23, 2026
Long-term environmental IoT/LPWAN deployments often aggregate heterogeneous data streams from diverse devices without systematic auditing of each variable's actual coverage prior to analysis-an increased risk when multiple sensor types coex…
- TENET: Time-point Encoding Network for Multivariate Time Series Anomaly DetectionDongchan Cho, Juwon Hwang, Keumyeong Kang, Jiho Han et al. · arXiv · Oct 23, 2026
In unsupervised multivariate time series anomaly detection (MTSAD), local variation can inflate reconstruction and forecasting errors, making observation-space discrepancy an unreliable indicator of abnormal system behavior. Since latent-sp…
- SKG in Practice: OOD Generalization Cases Across FourDomainsJian An, Chaoshi Wu, Xinpan Luo · arXiv · Oct 23, 2026
This paper presents the engineering implementation methods of the SKG inference framework and provides complete case studies across four domains. Case 1, 2D Dissipative Mechanical System: OOD MSE is 1.69 to 4.12 times lower than the best ne…
- EXPERIMENTAL CHARACTERIZATION OF MEASUREMENT CONSISTENCY AND TEMPORAL VARIATION IN AN ESP32 BASED IOT SYSTEM FOR BRIDGE MONITORINGAfouda Aristide YAI, Valéry Kouandété Doko, Thède AGBELELE, Mohamed Gibigaye · World Journal of Advanced R... · Oct 23, 2026
Structural health monitoring (SHM) relies on the systematic acquisition and temporal analysis of data that reflect structural behavior. Internet of Things (IoT) architectures offer considerable potential for developing distributed, connecte…
- Composite Score-Based Unsupervised Anomaly Detection Framework for Heat Treatment Process Temperature Data without Failure LabelsKyeong-In Mo, Kyoo-Sik Shin · Journal of the korean socie... · Oct 23, 2026
- Timing of the anthropogenic carbon invasion in the Southern California CurrentYéssica Vanessa Contreras-Pacheco, J. L. Abella-Gutiérrez, Gerardo Vallejo Espinosa, Juan Carlos Herguera · Biogeosciences · Oct 23, 2026
Abstract. The role of Eastern Boundary Upwelling Systems (EBUS), such as the southern California Current System, is a well-known high productivity region driven by alongshore winds, although their role as atmospheric carbon sources and sink…
- LACToS: Local Anomaly Detection via Conditional Typicality of SuperpixelsJihoon Hong, Alireza Kheirandish, Rohan Sanda, Sara Fridovich-Keil · arXiv · Oct 22, 2026
Local anomaly detection is the task of identifying spatially confined anomalous or out-of-distribution (OOD) regions within an otherwise in-distribution (ID) image. Most existing methods are designed for a specific context, with a strong fo…