The internal networks of cloud data centers are vast in scale, rich in data value, and high in traffic, imposing stringent demands on network security. Manual security operations for such network resources are highly resource-intensive and prone to errors. To address this, this paper proposes an autonomous network defense method for internal networks of cloud data centers based on reinforcement learning. We construct a leader-follower game model for network attack and defense, depicting the NP-hard interactive behavior in network attack and defense; we design a reinforcement learning defense agent that autonomously iterates learning, continuously feedback control, and adapts to environmental changes, training to solve for autonomous network defense strategies. Experiments demonstrate that our reinforcement learning agent acquires an excellent autonomous network defense capability, effectively resisting network attacks.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.