Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-9391
Main Title: Runtime Verification of P4 Switches with Reinforcement Learning
Author(s): Shukla, Apoorv
Hudemann, Kevin Nico
Hecker, Artur
Schmid, Stefan
Type: Conference Object
Language Code: en
Abstract: We present the design and early implementation of p4rl, a system that uses reinforcement learning-guided fuzz testing to execute the verification of P4 switches automatically at runtime. p4rl system uses our novel user-friendly query language, p4q to conveniently specify the intended properties in simple conditional statements (if-else) and check the actual runtime behavior of the P4 switch against such properties. In p4rl, user-specified p4q queries with the control plane configuration, Agent, and the Reward System guide the fuzzing process to trigger runtime bugs automatically during Agent training. To illustrate the strength of p4rl, we developed and evaluated an early prototype of p4rl system that executes runtime verification of a P4 network device, e.g., L3 (Layer-3) switch. Our initial results are promising and show that p4rl automatically detects diverse bugs while outperforming the baseline approach.
URI: https://depositonce.tu-berlin.de/handle/11303/10439
http://dx.doi.org/10.14279/depositonce-9391
Issue Date: 23-Aug-2019
Date Available: 4-Dec-2019
DDC Class: 000 Informatik, Informationswissenschaft, allgemeine Werke
Subject(s): network verification
P4
machine learning
fuzzing
Sponsor/Funder: EC/H2020/679158/EU/Resolving the Tussle in the Internet: Mapping, Architecture, and Policy Making/ResolutioNet
BMBF, 01IS17052, Adaptiver, Virtueller Assistent zur LAwinenwarnung Nach CHarakter Eigenschaften (AVALANCHE)
License: http://rightsstatements.org/vocab/InC/1.0/
Proceedings Title: Proceedings of the 2019 Workshop on Network Meets AI & ML - NetAI'19
Publisher: Association for Computing Machinery (ACM)
Publisher Place: New York, NY
Publisher DOI: 10.1145/3341216.3342206
Page Start: 1
Page End: 7
ISBN: 978-1-4503-6872-8
Notes: © ACM 2019. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 2019 Workshop on Network Meets AI & ML - NetAI’19, http://dx.doi.org/10.1145/3341216.3342206.
Appears in Collections:FG Internet Network Architectures (INET) » Publications

Files in This Item:
File Description SizeFormat 
shukla_etal_2019.pdfAccepted manuscript1.23 MBAdobe PDFThumbnail
View/Open


Items in DepositOnce are protected by copyright, with all rights reserved, unless otherwise indicated.