Sidebar[Skip]

Special Session 3:
Anomaly Detection in Complex and Evolving Systems

---

This special session aims to bring together researchers and practitioners working on the theory, algorithms, and applications of anomaly detection across diverse data-driven systems. As modern organizations increasingly rely on large-scale digital infrastructures, intelligent services, cyber-physical environments, and AI-enabled platforms, the ability to automatically identify unusual, unexpected, or abnormal patterns in data has become essential for ensuring system reliability, security, and operational efficiency. Anomaly detection plays a critical role in identifying rare events, emerging risks, operational failures, fraud, cyber threats, and unexpected system behaviors. However, real-world data environments are often characterized by high dimensionality, temporal dynamics, evolving data distributions, complex dependencies, and noisy observations. These characteristics pose significant challenges to traditional detection approaches and create opportunities for new methodological and application-driven research.

The goal of this special session is to provide a forum for presenting innovative research that advances anomaly detection methods and explores their applications across a wide range of domains. We particularly encourage work that integrates machine learning, deep learning, data mining, statistical modeling, and artificial intelligence techniques to improve the robustness, scalability, interpretability, and real-time capabilities of anomaly detection systems.

The session welcomes both theoretical contributions and application-oriented studies, including but not limited to anomaly detection in domains such as cybersecurity, Internet of Things (IoT), finance, healthcare, industrial systems, smart cities, transportation networks, and large-scale digital platforms.

Scope and topics:

This special session seeks to foster interdisciplinary collaboration and stimulate discussion on emerging research challenges, practical deployment issues, and future directions in anomaly detection. Researchers and practitioners from academia, industry, and government are encouraged to submit original contributions that present novel methodologies, theoretical insights, experimental studies, or real-world deployments.

Topics of interest include, but are not limited to:

• Machine learning and deep learning methods for anomaly detection
• Time-series and streaming anomaly detection in dynamic environments
• Unsupervised, semi-supervised, and self-supervised anomaly detection approaches
• Graph-based and network anomaly detection
• Explainable and interpretable anomaly detection models
• Early detection, predictive monitoring, and proactive anomaly management
• Robust anomaly detection under noise, missing data, or distribution shifts
• Anomaly detection in cybersecurity, fraud detection, and financial systems
• Anomaly detection for IoT, cyber-physical systems, and smart infrastructure
• Video, image, and multimodal anomaly detection
• Federated, distributed, and privacy-preserving anomaly detection
• Benchmark datasets, evaluation frameworks, and reproducibility in anomaly detection research
• Real-world applications and case studies of anomaly detection systems

Chairs:

• Chair Emails

Chair: Dr. Rashida Hasan: rashida.hasan@csun.edu
Co-Chair: Dr. Ruobin Qi


• Chair Biographies

Dr. Rashida Hasan is an Assistant Professor of Computer Science at California State University, Northridge, and Director of the Generalized Reasoning and Adaptive Intelligence (GRAIL) Lab. Dr. Hasan holds a Ph.D. in Computer Science from the University of Louisiana at Lafayette. Her research focuses on building robust and secure intelligent systems through anomaly detection, with applications in healthcare, finance, cybersecurity, and geospatial AI. In particular, she develops streaming anomaly detection frameworks that address concept drift and support continual learning, enabling adaptive models that remain reliable in dynamic and evolving environments. Her recent work has been published in leading IEEE, ACM, and Springer venues, including ICDM, ACM SAC, and ICMLA. She has served as a Technical Program Committee member for IEEE CCWC, IEEE AIIoT, IEEE IEMCON, and ACM SAC. In addition, she has contributed to the research community as a reviewer for several journals and conferences, including ACM SAC, FLAIRS, IEEE CCWC, and PeerJ Computer Science. Dr. Hasan has received several honors, including the Academic Excellence Award, the GHC Faculty Scholar Award, Best Paper Awards at IEEE IEMCON and IEEE CCWC, and the Outstanding Engineering Merit Award from the Engineering Council. Her vision is to advance robust and trustworthy AI systems capable of operating in complex and evolving environments, leveraging artificial intelligence for the greater good of society.

Dr. Ruobin Qi is an Assistant Professor of Computer Science specializing in the intersection of Machine Learning and Cyber-Physical System (CPS) Security. His research focuses on developing advanced unsupervised and semi-supervised anomaly detection frameworks to protect critical infrastructure from evolving cyber-physical threats. Dr. Qi has pioneered data-driven methodologies for electricity theft detection and cyber-attack identification within smart grids. His work specifically addresses the challenge of "unknown" attack vectors by leveraging deep representation learning and ensemble clustering to isolate malicious behavior in high-dimensional datasets. His scholarly contributions are featured in leading venues such as IEEE Transactions on Instrumentation and Measurement and Sustainable Energy, Grids and Networks. He holds a Ph.D. in Computer Science from the New Mexico Institute of Mining and Technology. His interdisciplinary background in both computer science and engineering allows him to bridge the gap between theoretical machine learning and practical industrial security applications.

Technical Committee

• Dr. Hasanul Mahmud, Visiting Assistant Professor, Department of Computer Science, Texas A & M International University, Texas, USA
• Dr. Seraj Mostafa, Research Collaborator, University of Maryland, Baltimore County (UMBC), USA
• Dr. Avijoy Chakma, Assistant Professor, Department of Computer Science, Bowie State University, Maryland, USA
• Dr. Vijay Srinivas Tida, Assistant Professor, Department of Computer Science, College of St. Benedict and St. John’s University, St. Joseph, Minnesota, USA
• Dr. Shamir Khandaker, Assistant Professor, Department of Computer Science, OklahomaCity University, Oklahoma, USA.

Paper Submission Instructions

All papers will be double-blind reviewed and must present original work.

• CMT Submission Site
• Select the track: Special Session 3: Anomaly Detection in Complex and Evolving Systems

Papers submitted for reviewing should conform to IEEE specifications. Manuscript templates can be downloaded from:

• IEEE website

Keydates

• Submission Deadline: June 20, 2026
• Notification of Acceptance: July 10, 2026

Registration

In order for your paper to be published in the proceedings you must register to the conference.

Paper Presentation Instructions

The papers submitted to this track will be presented in person as part of the conference. There is no virtual presentation for this session.