Federated Understanding of Security Information Over Networks
A DARPA ICAS Program
FUSION incorporates agent-less data connectors, machine learning-enabled data parsing, and semantic understanding to put multi-pivotal, relationship-centric queries at the operator’s fingertips. FUSION reuses existing, trusted remote connectivity and administration tools native to each device to retrieve local data sources with a combination of high level command line programs and scripts. It uses machine learning and a “cyber data” ontology to automatically map heterogeneous data and infer their semantics. This allows FUSION to index any data source, including those not previously seen. Finally, FUSION uses a graph database to allow new ways for operators to interact with and query the data. The graph model can dynamically accommodate any relationship within the data and reveal its interconnections.
- FUSION Administrative Overview Poster, November 2014 [PDF, 1.32 MiB]
- FUSION Technical Overview Poster, November 2014 [PDF, 1.64 MiB]
- FUSION CSAW THREADS Presentation, 13 November 2014 [PDF, 7.53 MiB]
- FUSION Overview Poster, May 2014 [PDF, 785 KiB]
- FUSION Video Presentation (720p, medium quality) [MP4, 12.3 MiB]
- FUSION Video Presentation (1080p, full quality) [MP4, 115.3 MiB]
FUSION is being developed by Digital Operatives LLC with funding from the Defense Advanced Research Projects Agency (DARPA). The views, opinions, and/or findings contained in these articles/presentations are those of Digital Operatives LLC and should not be interpreted as representing the official views or policies, either expressed or implied, of the Defense Advanced Research Projects Agency or the Department of Defense. Reference herein to any specific commercial product, process, or service by trade name, trademark or other trade name, manufacturer or otherwise, does not necessarily constitute or imply endorsement by DARPA, the Defense Department or the United States Government, and shall not be used for advertising or product endorsement purposes.