New Dawn Labs, working with the University of Dayton Research Institute (UDRI) and the Centauri Corp. proposes a cutting edge malware detection solution that is trained to identify threats based on known characteristics of existing malware for Industrial Controls Systems (ICS) and SCADA systems. Based on UDRIâs novel and published approach to malware classification and identification, and Centauriâs Integrated Civil Engineerâs Environment (ICEE) used to monitor and aggregate data on the Air Force Civil Engineering network (CE COINE), New Dawn is proposing an integrated platform for Malware Identification using Machine learning on the ICS (MIMICS) on the CE COINE network. ICS are deployed in manufacturing and warehousing facilities around the globe. They are usually under-supported and maintained by individuals that only understand how to install and configure these systems for their vendor and their equipment. The community at-large does not understand software/hardware, nor do they consider vulnerabilities, threats, and bad actors. The MIMICS platform offers a vendor-agnostic approach to identifying malware signatures on IT systems. It does this based on artificial intelligence that examines signatures of services and software running on an ICS computer. It does this by looking at the assembled code of the executable and performing pattern recognition on the programmed behavior of that software. This novel approach can be leveraged against many forms of malware, and used as a platform for new defense techniques in cyber protec
