ACD-G: Enhancing autonomous cyber defense agent generalization through graph embedded network representation

Show simple item record

dc.contributor.author Collyer, Josh
dc.contributor.author Andrew, Alex
dc.contributor.author Hodges, Duncan
dc.date.accessioned 2022-08-08T09:24:43Z
dc.date.available 2022-08-08T09:24:43Z
dc.date.issued 2022-07-23
dc.identifier.citation Collyer J, Andrew A, Hodges D. (2022) ACD-G: Enhancing autonomous cyber defense agent generalization through graph embedded network representation. In: 39th International Conference on Machine Learning (ICML 2022), 17-23 July 2022, Baltimore, Maryland, USA. (ML4Cyber workshop) en_UK
dc.identifier.uri https://icml.cc/
dc.identifier.uri https://dspace.lib.cranfield.ac.uk/handle/1826/18288
dc.description Presented at ML4Cyber Workshop : not included in the Proceedings of the 39th International Conference on Machine Learning en_UK
dc.description.abstract The adoption of autonomous cyber defense agents within real-world contexts requires them to be able to cope with differences between their training and target environments, bridging the simulation to real gap to provide robust, generalized defensive responses. Whilst the simulation to real gap has been studied in-depth across domains such as robotics, to date there has been minimal research considering generalizability in the context of cyber defense agents and how differences in observation space could enhance agent generalizability when placed into environments that differ from the training environment. Within this paper, we propose a method of enhancing agent generalizability and performance within unseen environments by integrating a graph embedded network representation into the agent’s observation space. We then compare agent performance with and without a graph embedded network representation based observation space within a series of randomized cyber defense simulations. We find that there is a trade-off between the effectiveness of the graph embedding representation and the complexity of the graph, in terms of node count and number of edges. en_UK
dc.language.iso en en_UK
dc.publisher International Conference on Machine Learning en_UK
dc.rights Attribution-NonCommercial 4.0 International *
dc.rights.uri http://creativecommons.org/licenses/by-nc/4.0/ *
dc.title ACD-G: Enhancing autonomous cyber defense agent generalization through graph embedded network representation en_UK
dc.type Conference paper en_UK


Files in this item

The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial 4.0 International Except where otherwise noted, this item's license is described as Attribution-NonCommercial 4.0 International

Search CERES


Browse

My Account

Statistics