| Title | Developing Proactive Defenses for Computer Networks with Coevolutionary Genetic Algorithms |
| Publication Type | Conference Paper |
| Year of Publication | 2017 |
| Authors | Lugo, Anthony Erb, Garcia, Dennis, Hemberg, Erik, O'Reilly, Una-May |
| Conference Name | Proceedings of the Genetic and Evolutionary Computation Conference Companion |
| Publisher | ACM |
| Conference Location | New York, NY, USA |
| ISBN Number | 978-1-4503-4939-0 |
| Keywords | cybersecurity coevolution, Evolutionary algorithms, Human Behavior, human factors, Network, pubcrawl |
| Abstract | Our cybersecurity tool, RIVALS, develops adaptive network defense strategies by modeling adversarial network attack and defense behavior in peer-to-peer networks via coevolutionary algorithms. Currently RIVALS DOS attacks are modestly modeled by the selection of a node that is completely disabled for a resource-limited duration. Defenders have three different network routing protocols. Attack or mission completion and resource cost metrics serve as attacker and defender objectives. This work also includes a description of RIVALS' suite of coevolutionary algorithms that explore archiving as a means of maintaining progressive exploration and support the evaluation of different solution concepts. To compare and contrast the effectiveness of each algorithm, we execute simulations on 3 different network topologies. Our experiments show that it is possible to forgo the assurance of monotonically increasing results and still retain high quality results. |
| DOI | 10.1145/3067695.3089234 |
| Citation Key | lugo_developing_2017 |
Developing Proactive Defenses for Computer Networks with Coevolutionary Genetic Algorithms