US DOE Office of Science logo

ASCR Cybersecurity Workshop

Sponsored by the U.S. Department of Energy,
Office of Advanced Scientific Computing research
Hilton Washington DC/Rockville Executive Meeting Center
Rockville, MD
January 7-9, 2015

Research Topic Descriptions

  1. Extreme Scale Power Grid Simulation: Research ideas should identify long-term (10-20 year) basic research challenges that will ensure a resilient power grid. This topic may explore scientific ideas and utilize extreme scale simulation of our national inter-networked power grid. The goal of this topic is to explore research and development that will lead to future tools, environments, and applications that will enable the study of power grid security via high fidelity scenarios, simulation, analysis, and optimization. Power grid roadmap:
  2. Trustworthy Supercomputing: Trustworthy computing is commonly applied to computing systems that are inherently secure, available, and reliable. The Committee on Information Systems Trustworthiness' publication, Trust in Cyberspace, defines such a system as one which "does what people expect it to do â€" and not something else â€" despite environmental disruption, human user, and operator errors, and attacks by hostile parties. Design and implementation errors must be avoided, eliminated, or somehow tolerated. It is not sufficient to address only some of these dimensions, nor is it sufficient simply to assemble components that are themselves trustworthy. Trustworthiness is holistic and multidimensional". The goal of this topic is to explore research areas within extreme high performance computing that can be influenced to incorporate a cybersecurity mindset during research and development. Some particular areas may include: Co-design to strategies that can influence future hardware designs so they have security built-in; Incorporate a cybersecurity focus to new and existing programs such as Resilience; X-Stack; Uncertainty Quantification; Data Management and Analytics; Large scale discrete event simulations, etc. Future research and development for exascale computing will be redesigning the stack; this represents a unique opportunity to include cyber objectives (Programing Languages, Operating System, Compilers, Runtime Systems, User Environments, Software verification; etc.). Resiliency and Trust: Correct computations and results in the presence of faults. Dynamic adaptive thread configuration and fault isolation, recovery and self-healing in exascale and beyond extreme performance leadership-class computing platforms.
  3. Trust within Open, High-End Networking and Data Centers: This topic will focus on research ideas that enable trust within an open shared environment among communications and data at rest or in transit minimizing security overhead. Emphasis should be placed on future requirements and need for high-end communication systems and applications where significant flexibility and application-specific optimization is required; optimized management of high throughput systems with extensive dynamic I/O connectivity; future platforms based on open standards that allow designers to use off-the-shelf building blocks supplied by a dynamic ecosystem; while delivering performance and security to millions of simultaneous subscribers. Next-generation networking needs more high-end real estate, (Viewed on August 18, 2014)
  4. Extreme Scale Data, Knowledge, and Analytics for Understanding and Improving Cyber Security: One particular challenge in cybersecurity is the ability to correlate, find, or detect patterns from heterogeneous sources of information such as the network, computing nodes, operating system, runtime, applications, etc. Another challenge is once important information is found, how to make and present the relevant information to the user in a meaningful and useful manner. Research ideas in this topic could focus on applying machine learning to discover attacks on networks and data, perform anomaly detection in event/traffic logs, achieve data fusion from multiple sources, analyze social and behavioral networks to identify anomalous behavior, and perhaps fingerprint HPC programs. Also, explore ideas that address data integrity and provenance to protect the integrity of science and evidence-based policy making.