Center for Information and Systems Assurance (CISA)
Information assurance at K-State began with early work in language-based security. In 2006, the Argus Group was formed to conduct research in cybersecurity. New research programs in computer security and information assurance have been created in the SAnToS Laboratory. These research projects and associated educational and outreach programs are all carried out under CISA. In 2010, CISA was designated a NSA/DHS National Center of Academic Excellence in Cyber Defense Research (CAE-R).
Cybersecurity Research Group
The research focus in this area is on distributed, fault-tolerant real-time embedded systems. We focus on both formal and informal methods for embedded system development. The initial target for development is on controller area networks used extensively for networking controls and actuators on-board machinery and vehicles. The group currently works on areas related to hard real-time systems whose operation depends not only on the correctness of the results, but also on their timeliness. Areas of interest include networking and operating system support for hard real-time embedded systems, specification and design languages for developing real-time embedded applications, and simulation and verification tools for ensuring their correctness.
Distributed Systems Lab (BeoCat)
BeoCat is K-State's Beowulf computing cluster. A cluster is, on the fundamental level, two or more computers that are used together to solve a problem. This type of computing, as it relates to research at K-State, is called high performance computing. High performance computing is an increasingly critical foundation for research across the disciplines, from improving the foundations of linguistic analysis to protecting lives through better bullet-resistant vests. At K-State, BeoCat provides critical computational resources for millions of dollars in current research grants, and is a strategic asset on pending proposals to various funding agencies. It is run by the Institute for Computational Research.
Intelligent Systems, Computer Architecture, Analytics, and Security (ISCAAS) Laboratory
The ISCAAS lab undertakes cutting edge research projects related to embedded and cyber-physical systems, secure and trustworthy systems, intelligent systems, computer architecture, parallel computing, distributed computing, data analytics, and artificial intelligence (AI) safety and security. The ISCAAS lab is currently undertaking the following projects:
- Design and tuning of parallel and reconfigurable architectures
- Design of secure and trustworthy systems
- Design of secure and dependable automotive cyber-physical systems
- Integrated fog, cloud, and Internet of things architectures
- Models and frameworks for adversarial attacks on intelligent systems and complex adaptive systems
- Development of plastic artificial neural networks-based lifelong learning machines
The AI Safety Reserach Initiative Blog provides more information and discussion about recent endeavors related to AI safety and security research undertaken by the ISCAAS laboratory.
Laboratory for Knowledge Discovery in Databases
The Laboratory for Knowledge Discovery in Databases (KDD) is a research group in the department of computer science. Its research emphasis is in the areas of applied artificial intelligence and knowledge-based software engineering for decision support systems. More specifically, we are interested in machine learning, data mining and knowledge discovery from large spatial and temporal databases, human-computer intelligent interaction, and high-performance computation in learning and optimization. In our research, we look for ways to systematically decompose analytical learning problems based upon information theoretic and probabilistic criteria, so that the most appropriate machine learning methods may be applied to the resulting transformed problems.
Machine Learning and Bioinformatics Group
The MLB group aims to design algorithms and develop tools for analyzing large amounts of data, in particular, molecular sequence and text data. Main projects focus on the following:
- design and development of semi-supervised and domain adaptation algorithms
- RNASeq analysis, alternative splicing discovery and gene prediction
- sentiment analysis and recommender systems
- ontology engineering and classifier learning from semantically heterogeneous data sources
Among others, the MLB group is collaborating with the Bioinformatics Center at Kansas State University to produce bioinformatics and genomics tools (funding from NSF and KSU Arthropod Genomics Center). It is also collaborating with the distributed systems lab to improve the infrastructure and enable Big Data research (funding from NSF), and with the Argus group on aiding intrusion detection systems using machine learning tools.
Multiagent and Cooperative Robotics Laboratory
The goal of the Multiagent and Cooperative Robotics Lab is to bring together researchers with a variety of expertise to solve interesting problems in the area of multiagent systems and cooperative robotics. Our research incorporates existing methodologies and techniques from other related disciplines – including artificial intelligence, robotics, and software engineering – into an integrated agent development methodology for multiagent systems. We are specifically interested in enabling teams of autonomous agents to organize and re-organize to accomplish their overall missions.
The Networked and Distributed Systems Security Group is doing research in areas of privacy and censorship resistance, medical system safety and security, ad hoc and low-power network security, and usable security. Projects include the following:
- compositional security and safety of dynamic medical systems
- large-scale censorship resistance
- low-power and ad hoc network security and user privacy
- usability of security software and password creation systems
Virtual Pipeline System Testbed
The objective of the proposed research is to develop and integrate compressor station and pipeline system component computer models into the Virtual Pipeline System Testbed (VPST). The VPST will simulate a pipeline system by determining the system pressures and gas flow rates, the emitted pollutant emissions, the fuel consumed, and the system “charge” as a function of time. The Virtual Pipeline System Testbed is sponsored by a grant from the Department of Energy. It is a collaborative research project conducted at Kansas State University in the National Gas Machinery Laboratory by faculty and graduate students in the departments of mechanical and nuclear engineering and computer science.