Detecting anomalies in realistic open-world settings is a fundamental challenge across diverse domains, including cybersecurity, healthcare, and finance. Traditional anomaly detection models often struggle to keep pace with dynamic environments where data distributions shift, new patterns emerge, and previously unseen data patterns arise. These limitations highlight the need for more adaptive, robust, and trustworthy approaches. Advancements in open-world anomaly detection have the potential to significantly improve decision-making in high-stakes applications, ultimately leading to more secure, efficient, and trustworthy AI-driven solutions.
This workshop aims to advance research in open-world anomaly detection by bringing together leading experts in dynamic learning, data stream mining, open-world learning, novelty detection, continual learning, and anomaly detection. By fostering collaboration across these fields, the workshop will address the critical challenges of identifying, adapting to, and explaining anomalies in complex, evolving data landscapes.
Paper submission deadline: August 29, 2025
Notification to authors: September 15, 2025
Camera-ready deadline: September 25, 2025
We encourage high-quality paper submissions on topics related to:
Continual Anomaly Detection: Adapting models to ongoing changes in data distribution while retaining past knowledge.
Open World Learning: Training models to recognize and adapt to new conditions with limited or no prior knowledge. This includes unsupervised, semi-supervised, and one-class learning.
Domain Adaptation: Transferring detection capabilities across different environments.
Challenging learning conditions: Handling missing data, imbalance, noise.
Other relevant topics include open-world anomaly detection in the following settings:
Concept Drift and Data Stream Mining
Multimodal and Multi-task Learning
Federated, Decentralized, and Privacy-Preserving Approaches
Active, Few-Shot, and Semi-Supervised Learning
Anomalous Pattern Mining and Discovery
Explainability in Continual Learning
Large Language Models
Graph Learning, Time Series, and Spatio-Temporal Learning
Unsupervised, Contrastive, and Adversarial Learning
Green AI and Model Compression for Learning in Constrained Environments
Neural Architecture Search for Task Mapping
The workshop’s focus is on anomaly detection in any real-world application, with special attention to the following key domains:
Cybersecurity: Intrusion detection, fraud detection, and malware identification.
Financial Data: Fraud detection and risk assessment in financial transactions.
Industrial and Sensor Networks: Fault detection, predictive maintenance, etc.
Cyberphysical Systems & Smart Grids: Anomalies in digital-physical infrastructures.
Medical Healthcare: Anomalies in medical imaging and electronic health records.
Social Networks: Misinformation detection, hate speech, and network security.
All papers must be submitted online via the wi-lab submission portal: Click here
Submitted manuscripts should use the ICDM 2025 paper template and be anonymized, i.e., papers must adhere to the IEEE 2-column format. For the regular paper track, submissions should not exceed 8 pages of content, plus an additional 2 pages for references. For the short paper track, submissions should be limited to a maximum of 4 pages of content, plus 1 extra page for references.
In alignment with the ICDM 2025 reviewing scheme, all submissions will undergo triple-blind reviews by the Program Committee, evaluating technical quality, relevance to the workshop scope, originality, significance, and clarity.
Duplicate submissions of the same paper are forbidden (including to more than one ICDM workshop). Papers must be original research. Submitting a paper substantially similar in content to a paper that has been accepted or is under consideration at another archival venue (conference or workshop with proceedings) is not allowed. During the review process, or after acceptance, submitted papers cannot be submitted to another archival venue unless substantial new material is added.
Accepted papers will be included in the ICDM Workshop Proceedings (separate from ICDM Main Conference Proceedings). The proceedings are published by IEEE and EI-indexed. Each accepted workshop paper requires a full registration.
A paid registration is required for each accepted paper, regardless of whether it is presented in person or via video.
Desk Reject Policy: Submissions that fail to adhere to the anonymity, length, or formatting requirements, or are affected by academic dishonesty issues, such as plagiarism, author misrepresentation, or falsification, may be subject to desk rejection by the chairs.
All accepted papers will be presented in person as posters during the workshop or as a pre-recorded video presentation.
Some papers will additionally be selected for spotlight presentations.