Preprint Article Version 1 This version is not peer-reviewed

Design and Verification of a Security Policy to Defense DDoS Attack for Cloud Robot

Version 1 : Received: 7 August 2018 / Approved: 8 August 2018 / Online: 8 August 2018 (08:54:39 CEST)

How to cite: Liu, B.; Cheng, J.; Li, Y.; Tang, X.; Chen, J. Design and Verification of a Security Policy to Defense DDoS Attack for Cloud Robot. Preprints 2018, 2018080164 (doi: 10.20944/preprints201808.0164.v1). Liu, B.; Cheng, J.; Li, Y.; Tang, X.; Chen, J. Design and Verification of a Security Policy to Defense DDoS Attack for Cloud Robot. Preprints 2018, 2018080164 (doi: 10.20944/preprints201808.0164.v1).

Abstract

Cloud robot is becoming popular and security of cloud robot is important. However, the researches of cloud robot safety are a few. This work develops a security policy to defense DDoS attack of cloud robot. In this policy, complex, but accurate calculation models are deployed on the cloud, simple but efficient calculation models are deployed on the robot. In the cloud, there are master server and standby server. The master server transfers parameters of complex but accurate models to the standby server periodically and the master executes the start-stop backup policy. Specifically, this work proposes and proves an algorithm to dynamically adjust the interval of parameter transfer. According to a PDRA feature of Netflow, when DDoS attacks, the master server sends warning signals to the robot and standby server. The robot runs local models to avoid stopping work until it is connected to the standby server. Then, standby server provides service to the robot until the master server recover. Finally, this work implemented a gesture recognition cloud robot based on convolutional neural network, hidden Markov model and PDRA feature of Netflow to verify the policy. Experiment shows that the security policy to defense DDoS attack for cloud robot is effective.

Subject Areas

Cloud robotic; Security policy; DDoS

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.