2026 IEEE Conference on Generative AI for Secure Systems (GAISS)

28-30 October 2026

The University of Texas at Austin, 110 Inner Campus Dr, Austin, TX 78705, United States

The main objective of GAISS'2026 is to bring together researchers, practitioners, and industry experts to explore the rapidly converging fields of Generative AI and cybersecurity. As generative models—from large language models to diffusion-based systems—reshape both offensive and defensive security landscapes, this conference aims to provide a rigorous, interdisciplinary platform for advancing the theoretical foundations, practical applications, and governance frameworks needed to secure these technologies responsibly. Spanning 19 specialized tracks, the conference addresses critical areas including threat intelligence, adversarial robustness, secure software development, critical infrastructure protection, quantum-enhanced security, privacy-preserving synthetic data, agentic AI systems, and red-team/blue-team automation. For researchers, the conference offers a unique opportunity to present cutting-edge work, engage in cross-disciplinary dialogue, access emerging benchmarks and datasets, forge collaborations across academia and industry, and shape policy discourse on the ethical and legal dimensions of secure generative AI—positioning participants at the forefront of a field defining the future of trustworthy, resilient AI-driven systems.

Important Dates

Paper Submission 30 July 2026
Paper Acceptance Notification After review of 2-3 reviewers
Regular Registration 15 August, 2026
Conference 28-30 October 2026

Note:

We welcome original contributions spanning core and applied research in Artificial Intelligence, Cybersecurity, and their intersection. Topics of interest include, but are not limited to:

Topics

  • Track 1 : Generative AI for Threat Intelligence & Adversary Simulation
  • Track 2 : Secure and Robust Generative Models in Adversarial Settings
  • Track 3 : Generative AI for Secure Software Development, DevSecOps & Code Generation
  • Track 4 : Generative AI in Critical Infrastructure, IoT & Cyber-Physical Secure Systems
  • Track 5 : Generative AI and Quantum Machine Learning for Secure Systems
  • Track 6 : Synthetic Data, Privacy-Preservation & Federated Generative Models
  • Track 7 : Generative AI for Secure Communications, Networking and Software-Defined Infrastructure
  • Track 8 : Human–AI Collaboration, Socio-Technical Impacts & Governance of Generative AI in Secure Systems
  • Track 9 : Generative AI for Red-Teaming, Automated Attack-Surface Generation & Blue-Team Automation
  • Track 10 : Emerging Foundations: Agentic & Autonomous Generative AI Systems in Secure Environments
  • Track 11 : Foundations and theory of generative AI for secure systems
  • Track 12 : Security, robustness, and safety of generative models
  • Track 13 : Privacy-preserving generative AI
  • Track 14 : Adversarial attacks and defenses involving generative systems
  • Track 15 : Secure architectures and deployment of foundation models
  • Track 16 : Agentic AI
  • Track 17 : Detection and mitigation of AI–enabled threats
  • Track 18 : Ethical, legal, and governance considerations for secure generative AI
  • Track 19 : Traditional AI includes Machine Learning, Deep Learning, Federated Learning and so on