Anthony Erb Lugo
Una-May O'Reilly
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.
- Erik Hemberg, Jacob Rosen, Geoff Warner, Sanith Wijesinghe, and Una-May OfiReilly. 2016. Detecting tax evasion: a co-evolutionary approach. Artificial Intelligence and Law 24, 2 (2016), 149--182. Google Scholar
Digital Library
- Elena Popovici, Anthony Bucci, R Paul Wiegand, and Edwin D De Jong. 2012. Coevolutionary principles. In Handbook of Natural Computing. Springer, 987--1033.Google Scholar
- Ion Stoica, Robert Morris, David Karger, M Frans Kaashoek, and Hari Balakrishnan. 2001. Chord: A scalable peer-to-peer lookup service for internet applications. ACM SIGCOMM Computer Communication Review 31, 4 (2001), 149--160. Google ScholarDigital Library
Index Terms
- Developing proactive defenses for computer networks with coevolutionary genetic algorithms
Recommendations
Investigating coevolutionary archive based genetic algorithms on cyber defense networks
GECCO '17: Proceedings of the Genetic and Evolutionary Computation Conference CompanionWe introduce a new cybersecurity project named RIVALS. RIVALS will assist in developing network defense strategies through modeling adversarial network attack and defense dynamics. RIVALS will focus on peer-to-peer networks and use coevolutionary ...
Adversarial co-evolution of attack and defense in a segmented computer network environment
GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference CompanionIn computer security, guidance is slim on how to prioritize or configure the many available defensive measures, when guidance is available at all. We show how a competitive co-evolutionary algorithm framework can identify defensive configurations that ...
Investigating algorithms for finding nash equilibria in cyber security problems
GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference CompanionDistributed Denial of Service (DDoS) cyber attacks continue to increase and cause disruptions in both industry and politics. As more critical information and services are provided through networks, it is important to keep these networks available. ...
Comments