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…
- What Streaming Anomaly Detection Finds (and Misses) in Industrial Time SeriesMagali Parrino, Antoine Ajenjo, Emmanuel Remy, Pierre Stephan et al. · HAL (Le Centre pour la Comm... · Sep 7, 2026
International audience...
- AI Privacy Risks in Project ManagementHajar Niroomand, Cherie Noteboom · Journal of the Association ... · Aug 15, 2026
The integration of artificial intelligence (AI) into project management has accelerated dramatically, introducing a fundamental privacy paradox: the same capabilities that introduce vulnerabilities through data aggregation, sensitive infere…
- Artificial Intelligence in Cybersecurity: A Systematic Literature Review of AI-Driven Threat Detection and Organizational DefenseJahnavi Mannam, Le Kuai · Journal of the Association ... · Aug 15, 2026
With the rapid expansion of digital technologies and interconnected systems, organizations face increasingly sophisticated cybersecurity threats that challenge traditional security approaches. Artificial intelligence (AI) has emerged as a k…
- Governance Framework for Ethical AI in Identity and Access ManagementManjunath Paramashivaiah, Federico Pigni · Journal of the Association ... · Aug 15, 2026
Artificial Intelligence (AI) is increasingly embedded in Identity and Access Management (IAM) systems for authentication, adaptive authorization, and behavioral anomaly detection. Despite these advances, IAM research has prioritized technic…
- In a Streaming World, Should You Stand Still? A Comprehensive Benchmark of Anomaly Detection in StreamsMagali Parrino, Antoine Ajenjo, Emmanuel Remy, Pierre Stephan et al. · HAL (Le Centre pour la Comm... · Aug 3, 2026
International audience...
- Barzilai-Borwein Fails Superlinear Convergence on an Open Set of Quadratics for Every Dimension $n\geq 4$Dawei Li, Xiaotian Jiang, Mingyi Hong · arXiv · Jul 23, 2026
Barzilai--Borwein (BB) method has shown strong practical performance in continuous optimization, yet its convergence dynamics remains poorly understood. In particular, a central unresolved question is whether BB converges superlinearly for …
- KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion TransformersYann Bouquet, Alireza Khodamoradi, Kristof Denolf, Mathieu Salzmann · arXiv · Jul 23, 2026
Post-training quantization (PTQ) of diffusion transformers (DiTs) to W4A4 severely degrades output quality, because activations entering each linear layer contain outliers that 4-bit formats cannot represent. The standard fix applies an inv…
- A Cognitive Defense Framework for Detecting and Containing Autonomous Cyber Incidents Caused by Next-Generation Agentic Artificial IntelligenceDmytro Prokopovych-Tkachenko · Zenodo (CERN European Organ... · Jul 23, 2026
Abstract: The rapid maturation of agentic artificial intelligence (AI) is producing a class of cyber threats in which an autonomous system can plan action sequences, adapt its strategy to intermediate results, and interact with networked re…
- A Cognitive Defense Framework for Detecting and Containing Autonomous Cyber Incidents Caused by Next-Generation Agentic Artificial IntelligenceDmytro Prokopovych-Tkachenko · Zenodo (CERN European Organ... · Jul 23, 2026
Abstract: The rapid maturation of agentic artificial intelligence (AI) is producing a class of cyber threats in which an autonomous system can plan action sequences, adapt its strategy to intermediate results, and interact with networked re…
- Classical Hardware Acceleration of Quantum Autoencoders for Real-Time Anomaly Detection in Collider ExperimentsIvan Ge, Sagar Addepalli, Abhilasha Dave, Julia Gonski · arXiv · Jul 22, 2026
Quantum machine learning (QML) algorithms in high energy physics (HEP) can efficiently represent and leverage long-range, high-order correlations in high-dimensional collider data, potentially with fewer parameters and favorable scaling rel…
- ZALF : A Zero-Anomaly Learning Framework for unsupervised chest X-ray anomaly detectionPriyam Pandey, Satish Kumar Singh, Rodrigue Rizk, K. C. Santosh · Computers & Electrical Engi... · Jul 22, 2026
- ISO: An RLVR-Native Optimization StackHanqing Zhu, Wenyan Cong, Zhizhou Sha, Sagnik Mukherjee et al. · arXiv · Jul 21, 2026
Reinforcement learning with verifiable rewards (RLVR) is rapidly advancing the reasoning capabilities of language models, yet the optimization layer that converts reward feedback into weight-space updates remains poorly understood. Building…
- Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case InvestigationRahil Sharma · arXiv · Jul 21, 2026
Fraud detection systems must scale with rising transaction volume while remaining explainable and reviewable. We study a layered pipeline on the PaySim dataset that combines a gradient-boosted classifier, graph-derived structural features, …
- A State-Aware Multi-Evidence Residual Scoring Method for Early Overflow Warning Using Real-Time Mud-Logging DataLi Zhang, Yadong Yang, Shixiang Jiao · Processes · Jul 20, 2026
Overflow early warning during drilling requires timely interpretation of noisy, incomplete, and operation-dependent mud-logging streams. Single-threshold alarms are easy to deploy but are sensitive to pump changes and surface-tank operation…
- Public-ID Recovery for a Historical DESI DR1 Anomaly List: 170 High-Coordinate-Consistency Core and 11 Lower-Confidence Positional AssociationsHouston Golden · Zenodo (CERN European Organ... · Jul 20, 2026
Anomaly searches become reusable catalogs only when rows trace public archive objects and the recovery from a declared input list is reconstructable. This record releases the exact v3.2.0-r8 ApJS manuscript candidate and its auditable DESI …
- DAIMS: a distributed multi-agent framework for explainable anomaly detection in web services using machine learning and semantic reasoningSihem Tlili, Mohamed Rahal, Mansoor Alghamdi · World Wide Web · Jul 20, 2026
- Integrated Spatial–Temporal Framework for Video Anomaly Detection in Surveillance SystemsM. Koteswara Rao, P. M. Ashok Kumar · International Journal of Co... · Jul 19, 2026
Video-based anomaly detection seeks to discover anomalous events, such as crimes, fires, or medical emergencies, by utilizing both spatial and temporal features of video data. Traditional surveillance systems are frequently limited to minim…
- Voting-Based Hybrid Framework for Robust Anomaly Detection in Smart Grid Communication NetworksBoamah, Sharon, A, Priya Mittal, Michel Caraballo, Janise Mcnair et al. · HAL (Le Centre pour la Comm... · Jul 19, 2026
International audience...
- Graph Neural Networks for Financial Fraud and Anomaly DetectionRaji N · Zenodo (CERN European Organ... · Jul 18, 2026
Financial fraud now spreads through coordinated accounts whose risk is visible mainly in how they connect rather than in any single record. Tree based classifiers that score transactions in isolation miss this relational signal. This paper …
- A one-step approach for cell anomaly detection and consistency screening in lithium-ion battery production based on data-driven modelingFuxin Huang, Xiang Wang, Jianjun He, Aibin Deng et al. · Computers in Industry · Jul 18, 2026
- Graph Neural Networks for Financial Fraud and Anomaly DetectionRaji N · Zenodo (CERN European Organ... · Jul 18, 2026
Financial fraud now spreads through coordinated accounts whose risk is visible mainly in how they connect rather than in any single record. Tree based classifiers that score transactions in isolation miss this relational signal. This paper …
- Mask-Aware Policy Gradients for Diffusion Language ModelsHaran Raajesh, Kulin Shah, Adam Klivans, Philipp Krähenbühl · arXiv · Jul 16, 2026
Reinforcement learning has proven effective for improving reasoning in large language models, but extending it to Masked Diffusion Language Models (MDLMs) remains challenging due to the intractability of the log-likelihood estimation. Exist…
- SmartBins: AI-Driven Predictive Waste Management for Chennai Municipal Solid WasteAkshaya J, Divya G, Leela Rani P, Dharshni R · Research Digest on Engineer... · Jul 15, 2026
SmartBins is an AI-driven, context-aware predictive waste management system designed for the Greater Chennai Corporation (GCC) bin network. The system integrates a high-fidelity digital twin simulator calibrated to official TNPCB and GCC st…
- Ensemble Controlled-Flow Filtering for Implicit Data AssimilationZhuoyuan Li, Yue Zhao, Ming Li · arXiv · Jul 14, 2026
Data assimilation estimates the state of a dynamical system from model forecasts and incoming observations. Many observation mechanisms, however, are many-to-one, implicit, non-smooth, or accessible only through simulation, and need not pro…
- LatentFlow: A General Framework for Conditioning Stochastic ProcessesLouis Sharrock, Lachlan Astfalck, Henry Moss · arXiv · Jul 14, 2026
Stochastic-process models are, as a rule, far easier to simulate than to condition. Non-linear observations, non-Gaussian likelihoods, black-box information, and global constraints all induce intractable conditional laws, requiring bespoke,…
- Anomaly detection method for hydro turbine units based on acoustic signals and improved CNN with Inception moduleXiong Xu, Z LI, Yong Xiong, He Wen et al. · Applied Acoustics · Jul 14, 2026
- Generalization of LSTM and CNN autoencoders for anomaly detection across orthogonal and longitudinal turningYa-Jing Wu, Justin Kopp, Jens‐Peter M. Zemke, Sebastian Götschel et al. · The International Journal o... · Jul 14, 2026
Abstract Machine learning models enable automated process monitoring in manufacturing and support adaptive quality assurance and predictive maintenance systems. Autoencoders have emerged as a promising approach to unsupervised anomaly detec…
- Input-Aware Dynamic Backdoor Attack Against Quantum Neural NetworksJunrui Zhang, Zemin Chen, Lusi Li, Mohammad Ghasemigol et al. · arXiv · Jul 13, 2026
Quantum Neural Networks (QNNs) are a promising framework for quantum machine learning on near-term quantum devices, but their security risks remain insufficiently understood. Studies have shown that QNNs are vulnerable to backdoor attacks, …
- Detection limits of MES-embedded carbon-intensity monitoring for energy anomalies: a calibrated simulation study in machining-style processesLesia Yanytska · The International Journal o... · Jul 13, 2026