Data Poisoning: Lightweight Soft Fault Injection for Python

Mohammad Amin Alipour; Alex Groce

Data Poisoning: Lightweight Soft Fault Injection for Python

Software Engineering 2016-11-07 v1

Authors: Mohammad Amin Alipour , Alex Groce

Abstract

This paper introduces and explores the idea of data poisoning, a light-weight peer-architecture technique to inject faults into Python programs. This method requires very small modification to the original program, which facilitates evaluation of sensitivity of systems that are prototyped or modeled in Python. We propose different fault scenarios that can be injected to programs using data poisoning. We use Dijkstra's Self Stabilizing Ring Algorithm to illustrate the approach.

Keywords

data poisoning attack

Cite

@article{arxiv.1611.01501,
  title  = {Data Poisoning: Lightweight Soft Fault Injection for Python},
  author = {Mohammad Amin Alipour and Alex Groce},
  journal= {arXiv preprint arXiv:1611.01501},
  year   = {2016}
}

Comments

Draft- 6 pages

Related papers

View all related →