Improving rippled: Leveraging passive model inference techniques to test large decentralized systems

Bachelor thesis (2020)

Authors

S. Karayalçin Electrical Engineering, Mathematics and Computer Science

Contributors

S. Roos Data-Intensive Systems - EEMCS (mentor)
S. Prabhu Kumble Data-Intensive Systems - EEMCS (graduation committee member)
Ranga Rao Venkatesha Prasad Embedded Systems - EEMCS (graduation committee member)
Faculty
Electrical Engineering, Mathematics and Computer Science, Electrical Engineering, Mathematics and Computer Science
Copyright: © 2020 Sengim Karayalçin
More Info
expand_more

Published Date

25-06-2020

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

Blockchains and cryptocurrencies, like Ripple, are becoming more widely used. Testing the large decentralized systems these technologies on is complex, as the behavior of the system is dependent on many external factors. We will examine the viability of using passive model inference techniques to test the systems based on the network traffic they produce. Passive inference techniques have been used extensively to model and test different types of systems. However, it is unclear how well passive model inference techniques work for inferring models of large decentralized systems based on the network traffic that these systems produce. Here we show that detecting bugs in the implementations of decentralized protocols is possible. These results were achieved by simulating a version of the Ripple network and modeling the workings of a node in this network. We also simulated the network with defective nodes and by observing the different models generated, were able to detect these bugs. Our results suggest that using passive model inference techniques on network traffic can help test large decentralized systems.