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 · 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…
- From Protocols to Evidence: Bounded Claims for AI in Service of the Common GoodNitesh V. Chawla, Paulo Benanti · arXiv · Sep 10, 2026
Artificial Intelligence does more than create a governance problem. It can also reveal where institutions have already failed to provide responsiveness, belonging, care, and accountability. Once deployed, AI becomes an intervention in those…
- A Dataset and Model for Imputing Water Surface Elevation on a Large and Extremely Sparse Spatiotemporal GraphRuben Cartuyvels, Karim Douch, Gabriele Bertoli, Mounia El Baz et al. · arXiv · Sep 10, 2026
Continuous monitoring of water surface elevation across river networks is critical for flood forecasting, water resource management, and understanding the global water cycle. Yet, the scarcity of in situ gauges across much of the globe cons…
- HERALD: High-Fidelity Exemplar Retrieval with Adaptive Landmark Distillation for Heterophily-Aware Graph CondensationSujan Chakraborty, Priyanka Saha, Saptarshi Bej · arXiv · Sep 10, 2026
Graph condensation aims to produce a small surrogate graph that preserves the downstream node-classification performance of a much larger original graph. Existing methods rely on Weisfeiler-Lehman neighbourhood aggregation or gradient-based…
- Lightweight autoencoder-based anomaly detection for CAN bus in competition motorcycles designed for ARM Cortex-M7Andrei García Cuadra · Journal of Information Secu... · Sep 10, 2026
- FCAE-Mixer: frequency-aware convolutional autoencoder with dual-branch mixing for time series anomaly detectionLongfei Li, Yinghua Tong · Scientific Reports · Sep 10, 2026
Abstract The core of complex time series anomaly detection lies in the effective extraction of multi-dimensional features. However, existing methods often separate the synergistic mechanism among local temporal, global variable, and frequen…
- Deep Learning Based Temporal Anomaly Detection in ABS Braking SystemsHaneul Moon, Sungjin Lee, Seongkeun Park · Transactions of Korean Soci... · Sep 10, 2026
- VeilGuard: A Multi-Modal AI Framework for Detecting Hidden Communications, Covert Payloads, and Emerging Cyber ThreatsEugene Ezenwa Ebem · Zenodo (CERN European Organ... · Sep 10, 2026
VeilGuard presents a multimodal artificial intelligence framework for identifying hidden communications, covert payloads, and emerging cyber threats across heterogeneous digital content. The proposed architecture combines AI-driven content …
- Likelihood-free inference with nuisance parameters through normalizing flowsPhil Assheton · arXiv · Sep 9, 2026
We present a simple decomposition of a neural-network-based normalizing flow that naturally uncovers a pivotal statistic (or something close) in the presence of nuisance parameters, based only on a sample generator from the distribution of …
- Searching for New Physics with Reinforcement LearningJacky Kumar, Marianne Bouchard, David London · arXiv · Sep 9, 2026
Finding new physics (NP) is the most important problem in particle physics today. Studying ``anomalies'', i.e., measurements of low-energy observables whose values disagree with the predictions of the Standard Model (SM), is a powerful sear…
- TRACE: Training Reasoning Agents for Causal Exploration with Synthesized RewardsRui Sun, Zhan Shi, Bing He · arXiv · Sep 9, 2026
Reinforcement learning with verifiable rewards (RLVR) has advanced language-model reasoning in domains such as mathematics and code, where objective answers are inexpensive to check. Diagnostic reasoning over complex data lacks this advanta…
- A review and synthesis of the Consultative Group on International Agricultural Research’s work on climate-induced extreme rainfall and floods, 2012–2023Claudious Chikozho, A. Mukherji, C. Bosire, K. Kujinga et al. · Agriculture & Food Security · Sep 9, 2026
In recent decades, the increased frequency of extreme rainfall events has significantly affected agri-food systems, accounting for 19% of the total crop damage across the world and 18–43% of observed anomalies in global crop yields. Some st…
- An intelligent optimization method for communication monitoring alarm threshold based on BeiDou satellite positioning dataAn Lu, Yue Long, Fan JiFeng, Liang FaLiang et al. · Discover Computing · Sep 9, 2026
This paper proposes an intelligent optimization method for BeiDou communication monitoring alarm thresholds based on Representation Learning and Adaptive Thresholding for Anomaly Detection (RLAT-AD), aiming to address the issue that under c…
- Stability of Circumbinary Orbits in Misaligned Triple-star SystemsStephen Lepp, Rebecca G. Martin · The Astrophysical Journal · Sep 8, 2026
Abstract We investigate the stability of circumbinary orbits in hierarchical triple-star systems, focusing on the effects of a misaligned outer companion star. Test particles are subject to competing gravitational torques from the inner bin…
- A Comparative Study of Local-Global Anomaly-Map Fusion Strategies in EfficientADQinyu Xiao · Applied and Computational E... · Sep 8, 2026
Industrial anomaly detection must identify both local structural defects and global logical violations while preserving localization quality and practical inference cost. EfficientAD provides complementary local student-teacher and global a…
- Quantifying atmospheric and land drivers of hot temperature extremes through explainable Artificial IntelligenceAlejandro Mesa, Lluís Palma, Markus G. Donat, Stefano Materia et al. · Weather and Climate Dynamics · Sep 7, 2026
Abstract. Different drivers have been shown to play a central role in modulating the occurrence and intensity of summer temperature extremes, yet their individual contributions remain difficult to quantify. In this study, we develop an expl…
- Beyond gait speed: a multidimensional motor signature of motoric cognitive risk syndrome identified through domain-specific anomaly detectionBaptiste Perthuy, Hugues Vinzant, Clement Brifault, Vincent Cabibel et al. · GeroScience · Sep 7, 2026
- Unraveling TeV halos with the Cherenkov Telescope ArrayDan Hooper, Elena Pinetti, Anastasia Sokolenko · The European Physical Journ... · Sep 7, 2026
Abstract Pulsars are observed to emit bright and spatially extended gamma-ray emission at multi-TeV energies. These so-called “TeV halos” are now understood to be a nearly universal feature of middle-aged pulsars. However, many of the key p…
- Machine learning is good for physics—and vice versaMichael Krämer, Tilman Plehn · The European Physical Journ... · Sep 6, 2026
Abstract Scientific AI is rapidly transforming fundamental physics research and challenging defining aspects of the fundamental physics methodology. We discuss opportunities and dangers of this transformation and find exciting benefits from…
- A drift adaptive framework for detecting and tracking evolving anomalies in financial transaction streamsFrancis Thiong'o, Lawrence Nderu, Ronald Waweru Mwangi, Isaac Nyabisa Oteyo · Scientific Reports · Sep 6, 2026
Abstract Financial fraud detection is increasingly challenged by concept drift, evolving transaction behaviour, and adversarial adaptation, which can degrade conventional anomaly-detection methods under distributional change. Although unsup…
- Computer Vision and Artificial Intelligence-Driven Structural Health Monitoring in Water Conservancy: Intelligent Early Warning and Economic Benefit OptimizationYunshu Luo, Hanwen Xue · Asia Pacific Economic and M... · Sep 6, 2026
Water conservancy structures serve as the core infrastructure for the operation of water conservancy projects; their structural health directly impacts regional flood control safety, water resource supply security, and ecological environmen…
- Vision-guided multi-image prompt learning for zero and few-shot pipeline anomaly detectionChunlei Wu, Yonghao Wang, Bai Qiao, Huan Zhang · Multimedia Systems · Sep 6, 2026
- GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly DetectionXudong Wang, Chris Ding, Tongxin Li, Jicong Fan · arXiv · Sep 4, 2026
We introduce GLASS, a framework for graph-level anomaly detection (GLAD) that achieves robust cross-domain transferability through graph-language alignment on the unit hypersphere. GLASS builds a unified representation space by aligning a s…
- Advanced chronic kidney disease in children with CAKUT: a retrospective cohort study in SenegalLissoune Cissé, Faty Balla Lo, Pape Alassane Mbaye, Doudou Gueye et al. · BMC Pediatrics · Sep 4, 2026
Abstract Background Congenital anomalies of the kidney and urinary tract (CAKUT) are the leading cause of chronic kidney disease (CKD) in children worldwide. In low-resource settings, delayed diagnosis and limited access to specialized neph…
- Spin Polarized Transport in Copper Oxide Atomic Junctions Revealed by Anomalous Shot Noise Behavior in the Presence of the Kondo EffectMarcel Strohmeier, Samanwita Biswas, Wolfgang Belzig, Regina Hoffmann-Vogel et al. · Nano Letters · Sep 4, 2026
Abstract Noise measurements provide a valuable tool for revealing spin polarization effects in the electronic transport through quantum coherent conductors. We present an extension of the Landauer description of shot noise to include energy…
- Beyond wind-induced upwelling: diverse drivers of future productivity in eastern boundary upwelling systemsErica Cioffi, Laurent Bopp, Lester Kwiatkowski · Biogeosciences · Sep 4, 2026
Abstract. Eastern Boundary Upwelling Systems (EBUS) contribute disproportionately to global marine productivity and fisheries, yet their response to climate change remains poorly understood. Given the essential ecosystem services they suppo…
- LiteFDNet: A Lightweight Deep Network for Cardiotocography-Based Fetal Distress DetectionFan Feng, Qinglei Shi, ziyue yuan, Fangyi Wu et al. · Biomedical Signal Processin... · Sep 4, 2026
This retrospective single-center study developed and evaluated LiteFDNet, a lightweight deep neural network for intrapartum fetal distress detection from cardiotocography (CTG). All eligible deliveries from April 2014 to December 2024 were …
- Parameterised graph theory for tensor networks: entanglement rerouting, structural simplification, and agnostic tomographyMatthias C. Caro, Natalie McHugh, Sergii Strelchuk · arXiv · Sep 3, 2026
Parameterised graph theory studies how the complexity of graph-theoretic problems depends on structural parameters of the input graph. This perspective has proved useful in analysing tensor-network simulation (Markov and Shi, 2008). Its imp…
- Constant regret in general games via higher-order optimismOmar Abbadi, Rida Laraki, Panayotis Mertikopoulos · arXiv · Sep 3, 2026
We introduce an uncoupled learning algorithm which, when employed by all players of an arbitrary $N$-player normal form game with up to $K$ actions per player, guarantees $O(N^3\log^2 K)$ individual regret, uniformly over the horizon of pla…
- LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style UpdatesDmitrii Andriianov, Andrey Veprikov, Aleksandr Beznosikov · arXiv · Sep 2, 2026
Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that…