CCNI Workshop

The 10th Workshop on Graph Techniques for Adversarial Activity Analytics (GTA³ 2026)

Dec 14, 2026 | Phoenix, Arizona, USA

For past GTA3 workshops, please visit our archive page.

In conjunction with the 2026 IEEE International Conference on Big Data (https://bigdataieee.org/BigData2026/)

Workshop Summary

Graphs are powerful analytical tools for modeling complex, dynamic interactions across a wide range of domains and applications. They enable insights into interconnected systems such as cybersecurity, critical infrastructure, finance, communication, and transportation, where understanding relationships and patterns is essential. At the same time, rapid advances in generative AI are transforming how information, signals, and behaviors are created and propagated. These developments are increasing both the scale and sophistication of coordinated and deceptive activities across such systems. As a result, there is a growing need for advanced, adaptive methods capable of analyzing large-scale graph-structured data, detecting emerging patterns, and supporting timely, reliable decision-making.

This workshop aims to bring together researchers and practitioners to explore emerging challenges and innovative approaches in graph analysis in the era of generative AI, with an emphasis on scalability, trustworthiness, and real-world impact. Key challenges in this space include reasoning over heterogeneous and partially observed graphs, aligning patterns across distributed sources, and detecting subtle signals in large-scale, noisy environments. Furthermore, graph-based methods must remain robust to adaptive manipulation and shifting data patterns influenced by generative AI.

To structure these challenges, the workshop focuses on three fundamental problems in graph-based adversarial activity analytics: “Connecting the Dots,” “Finding a Needle in a Haystack,” and “Defending Against Attacks.” Through this lens, we aim to advance state-of-the-art techniques and foster new approaches to tackling adversarial dynamics in this evolving landscape.

Topics of Interest

Including but not limited to:

  • Graph alignment and integration from heterogeneous domains
  • Subgraph detection and discovery for large networks
  • Attack and defense strategies on graph models
  • Generative models for synthesizing realistic networks (e.g., static, dynamic, etc.)
  • Representation learning on graphs
  • Multilayer and multiplex networks
  • High-performance graph computing
  • Explainability of graph models (e.g., GNNs)
  • Federated Graph Machine Learning
  • Limits of detectability and identifiability
  • Link prediction and recommendation
  • Information diffusion and influence maximization
  • New methods for clustering and ranking on graphs
  • Novel datasets and evaluation metrics for network analytics
  • Knowledge graph creation, mining, and applications
  • Knowledge graph completion and reasoning
  • Complex anomaly detection and interpretation
  • Summarization and visualization of large networks
  • Interactive graph search and exploration
  • Topological analysis (e.g., motif analysis) on large graphs
  • Game-theoretic approach for adversarial modeling on graphs
  • Graph-based semi-supervised learning, active learning, and transfer learning
  • Frontiers of graph machine learning for adversarial activities analytics
  • Large language models and generative AI for adversarial activities.
  • Weakly supervised and self-supervised anomaly detection.
  • Fairness, explainability and privacy in adversarial activities analytics.
  • Benchmarks for adversarial activities analytics.

Submission Instructions

Submissions to the workshop will be subject to a double-blind peer review process, with each submission reviewed by at least two program committee members and an organizer. Submissions will be evaluated based on their relevance to the workshop, scientific novelty, and technical quality. Accepted papers will be given a presentation slot in the workshop and will be included in the IEEE Big Data Workshop Proceedings.

We accept papers between 6 to 10 pages in length, including shorter works-in-progress and full papers presenting mature research. All submissions must follow the two-column IEEE format. More details are available on the IEEE Big Data Paper Submission page.


Important Dates

  • + Workshop paper submission: TBD date in Oct 2026
  • + Notification of workshop paper acceptance: TBD date in Nov 2026
  • + Camera-ready submission deadline: TBD date in Nov, 2026
  • + Workshop date:Dec 14, 2026 (tentative)

Keynote Speakers

We plan to invite 3 ~ 4 speakers who are experts in relevant research areas.

Program Chairs (Organizers)