AInception main aim is to develop novel AI-based tools and techniques for detection and response: from detecting adversarial behaviour from logs and network traffic; to understanding, contextualizing and explaining the detected threat; to generating risk and impact aware response action; all the way to automating the execution and evaluation of the response action on the underlying infrastructure. AI will play a central role for all these steps in the AInception tool pipeline. These tools will be combined into a proof-of-concept end to-end detection and response prototype, evaluated in operational scenarios with end users.
The AINCEPTION consortium is composed of 18 different organisations from 9 different EU Member States (Greece, Norway, France, Cyprus, Sweeden, Netherlands, Austria, Bulgaria, Italy).
The AInception consortium is highly diverse, both in terms of type of partners, as well as geographical distribution. It brings together 4 Large industrial partners (TSGF, THH, NG, CY4GATE), 2 Midcaps (SPH, MNEMONIC), 3 SMEs (INFILI, 8BELLS, UBITECH), 5 RTOs (TNO, KTH, NCSRD, AIT, CEA) and 4 purely defence research institutes (FFI, FOI, BDI, HMOD).
We are proud to announce that the paper title "Mission-Aware Cyber Incident Response Generation Using Reinforcement Learning" received the Best Paper Award at the International Conference on Military Communication and Information Systems (ICMCIS) 2025.
The paper, sponsored by AInception.eu (AInception), was showcased at the NATO Science and Technology Organization's IST Panel conference on May 13-14, 2025.
Special recognition goes to the authors: Aws Jaber (KTH), Monica Endregard, Federico Mancini and Gudmund Grov (FFI).