Robustifying network protocols with adversarial examples

Tomer Gilad, Nathan H. Jay, Michael Shnaiderman, Brighten Godfrey, Michael Schapira

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Scopus citations


Ideally, network protocols (e.g., for routing, congestion control, video streaming, etc.) will perform well across the entire range of environments in which they might operate. Unfortunately, this is typically not the case; a protocol might fail to achieve good performance when network conditions deviate from assumptions implicitly or explicitly underlying its design, or due to specific implementation choices. Identifying exact conditions in which a specific protocol fares badly (though good performance is feasible to attain) is, however, not always easy as the reasons for protocol suboptimality or misbehavior might be elusive. We make two contributions: (1) We present a novel framework that leverages reinforcement learning (RL) to generate network conditions in which a given protocol fails to perform well. Our framework can be used to assess the robustness of a given protocol and to guide changes to the protocol for making it more robust. (2) We show how our framework for generating adversarial network conditions can be used to enhance the robustness of RL-driven network protocols, which have gained substantial popularity of late. We demonstrate the usefulness of our approach in two contexts: adaptive video streaming and Internet congestion control.

Original languageAmerican English
Title of host publicationHotNets 2019 - Proceedings of the 18th ACM Workshop on Hot Topics in Networks
PublisherAssociation for Computing Machinery, Inc
Number of pages8
ISBN (Electronic)9781450370202
StatePublished - 13 Nov 2019
Event18th ACM Workshop on Hot Topics in Networks, HotNets 2019 - Princeton, United States
Duration: 14 Nov 201915 Nov 2019

Publication series

NameHotNets 2019 - Proceedings of the 18th ACM Workshop on Hot Topics in Networks


Conference18th ACM Workshop on Hot Topics in Networks, HotNets 2019
Country/TerritoryUnited States

Bibliographical note

Publisher Copyright:
© 2019 ACM.


Dive into the research topics of 'Robustifying network protocols with adversarial examples'. Together they form a unique fingerprint.

Cite this