ACTION researchers have organized the inaugural Workshop on Agentic AI in Offensive and Defensive Cyber Operations (AIDC'26), to be held in conjunction with the 2026 Annual Computer Security Applications Conference (ACSAC 2026) in December in Los Angeles, CA.
As described at aidcworkshop.github.io/, The goal of AIDC is to bring together researchers, practitioners, and policymakers from academia, industry, and government to advance the theory, methodology, and practice of agentic security. By establishing a shared space for adversarial AI specialists and cybersecurity operational experts, the workshop intends to transition the community from isolated model evaluations toward holistic, dynamic, and resilient systems design.
Topics of interest include
- Autonomous Offensive Operations
- Autonomous Defensive Countermeasures
- Model-on-Model Adversarial Interaction
- Evaluation Environments and Benchmarks
- Theory, Specification, and Governance
Kerri Pinos (Horizon3) and Z. Berkay Celik and Dongyan Xu (Purdue University) are co-charing the exciting symposium. Snehal Antani (Horizon3) and Giovanni Vigna (UC Santa Barbara) make up the steering committee. The program committee is made up of faculty and researchers from Purdue, Dynatrace, AWS, Walmart, Georgia Tech, UIUC, and Arizona State.
Paper submissions are due September 25, 2026 AoE. Visit aidcworkshop.github.io/ for more information and submission guidelines.