The 3nd International Workshop on Autonomous Cybersecurity

The 3rd edition of AutonomousCyber 2026 represents a continued effort to advance research and development in autonomous cybersecurity. Following the success of our inaugural event, AutonomousCyber 2024, co-located with the 31st ACM Conference on Computer and Communications Security (ACM CCS 2024) in Salt Lake City, USA and the second edition, AutonomousCyber 2025, held at ESORICS 2025 in Toulouse, France, the 2026 edition will be co-located with the 31st European Symposium on Research in Computer Security (ESORICS 2026), a premier venue for security and privacy research.

AutonomousCyber Workshop presents an exciting opportunity to explore state-of-the-art methodologies, groundbreaking technologies, and real-world applications. We solicit original, unpublished, and innovative research work relevant to the theme of this workshop. We seek contributions in, but are not limited to, the following key areas of interest and topics:

Foundational and Theoretical Advances:

Cognitive models for enhancing threat intelligence

Principles and theory of self-learning cybersecurity systems

Advances in QML for proactive cyber defence

Human–machine teaming for cyber resilience

Formal models of autonomous defensive decision-making

Verification and assurance of agentic cyber defense behaviour

Evaluation metrics for autonomy, reliability, and safety

Autonomous Cybersecurity Techniques & Methods:

AI-driven threat detection and mitigation algorithms

Development of simulators for testing autonomous security systems

Architectural innovations for adaptive and self-improving cybersecurity

Predictive modeling and proactive defence strategies:

Integration of autonomous defences with large-scale networked and distributed systems

AI agents for continuous assurance and compliance

LLM-based reasoning for adaptive defense orchestration

Autonomous vulnerability discovery and patch synthesis

Benchmarks and datasets for evaluating autonomy in cybersecurity

Planning and tool-use in cyber defense agents

Memory, reasoning, and state tracking for security agents

Adversarial attacks against autonomous cyber agents

Guardrails and runtime monitors for autonomous security systems

Practical Applications and Case Studies:

AI-based automated patch management and incident response

Autonomous digital forensics and independent security investigations

Real-world implementations and lessons learned from deployed autonomous security solutions

Autonomous SOC operation and AI security copilots

Autonomous response in cyber-physical and critical infrastructure systems

Evaluation of autonomous systems in operational and adversarial environments (e.g., red-teaming, CTFs, SOC scenarios)

Ethical, Legal, and Operational Considerations:

Regulatory challenges of deploying autonomous cybersecurity systems

Ethical considerations in self-adaptive AI-driven cyber defences

Continuous compliance monitoring with AI-driven systems

Accountability and governance of action-taking AI defenders

Human oversight and escalation policies in autonomous defense

Safety, reliability, and trust frameworks for autonomous cybersecurity systems

We encourage contributions that offer novel insights, theoretical advancements, empirical evaluations, and reflections on real-world implementations in AutonomousCyber 2026. This workshop aims to foster a deeper understanding of autonomous systems in cybersecurity and their pivotal role in shaping the future of digital security.

Workshop Organizers:

Ali Dehghantanha, Canada Research Chair and Professor, University of Guelph, ON, Canada

Reza M. Parizi, Director of Decentralized Science Lab and Professor, Kennesaw State University, USA

Gregory Epiphaniou, Associate Professor of Security Engineering, University of Warwick, UK

Workshop Chairs:

Ali Dehghantanha, University of Guelph, ON, Canada

Reza M. Parizi, Kennesaw State University, USA

Gregory Epiphaniou, University of Warwick, UK

Publication Chair:

Abbas Yazdinejad, University of Regina, SK, Canada

Publicity Chair:

Tooska Dargahi, Manchester Metropolitan University, UK

Tao Li, City University of Hong Kong, Hong Kong