DARPA funds cognition, regeneration projects
- By Dawn S. Onley
- Apr 16, 2004
The Defense Advanced Research Projects Agency has chosen 11 research projects to fund under its Self-Regenerative Systems program.
The 18-month effort seeks technologies that help military systems to learn and to regenerate themselves. The chosen research will develop technologies for military computer systems that can hold up under errors or attacks.
Each of the 11 projects will receive $815,000 to $1.3 million, according to a DARPA announcement yesterday.
'SRS technology will make possible advanced military systems that remain potent for extended deployment periods even in the face of sophisticated and sustained attack,' DARPA's statement said.
The program will focus on four technology areas:
- Biologically inspired diversity: generating many variants of a system component that perform the same functions but with sufficiently different vulnerabilities that an attack can only damage a small part of the entire system. Two projects were selected, from the University of Virginia in Charlottesville, Va., and Global InfoTek Inc. of Reston, Va.
- Cognitive immunity and regeneration: techniques that recognize damage from an attack and automatically recover operational capability even under continual attacks. Three of the four projects come from the Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory in Cambridge, Mass.; the fourth is from Honeywell Labs of Minneapolis.
- Granular, scalable redundancy: maintaining multiple copies of selected components to swap in case of damage. The program will develop new techniques for coordinating high-performance military systems. Three projects were chosen from Carnegie Mellon University in Pittsburgh, Johns Hopkins University in Baltimore and Cornell University in Ithaca, N.Y.
- Reasoning about insider threats: technology to estimate the probability of a malicious military operator. Two projects were funded from the Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory in Cambridge, Mass., and Telecordia Technologies in Morristown, N.J.
More information about the SRS projects appears online