PyTorchFI: A Runtime Perturbation Tool for DNNs

Abdulrahman Mahmoud, Neeraj Aggarwal, Alex Nobbe, Jose Rodrigo Sanchez Vicarte, Sarita V. Adve, Christopher W. Fletcher, Iuri Frosio, Siva Kumar Sastry Hari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

PyTorchFI is a runtime perturbation tool for deep neural networks (DNNs), implemented for the popular PyTorch deep learning platform. PyTorchFI enables users to perform perturbations on weights or neurons of DNNs at runtime. It is designed with the programmer in mind, providing a simple and easy-to-use API, requiring as little as three lines of code for use. It also provides an extensible interface, enabling researchers to choose from various perturbation models (or design their own custom models), which allows for the study of hardware error (or general perturbation) propagation to the software layer of the DNN output. Additionally, PyTorchFI is extremely versatile: we demonstrate how it can be applied to five different use cases for dependability and reliability research, including resiliency analysis of classification networks, resiliency analysis of object detection networks, analysis of models robust to adversarial attacks, training resilient models, and for DNN interpertability. This paper discusses the technical underpinnings and design decisions of PyTorchFI which make it an easy-to-use, extensible, fast, and versatile research tool. PyTorchFI is open-sourced and available for download via pip or github at: https://github.com/pytorchfi

Original languageEnglish (US)
Title of host publicationProceedings - 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN-W 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages25-31
Number of pages7
ISBN (Electronic)9781728172637
DOIs
StatePublished - Jun 2020
Event50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN-W 2020 - Valencia, Spain
Duration: Jun 29 2020Jul 2 2020

Publication series

NameProceedings - 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN-W 2020

Conference

Conference50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN-W 2020
CountrySpain
CityValencia
Period6/29/207/2/20

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality
  • Control and Optimization
  • Health Informatics

Fingerprint Dive into the research topics of 'PyTorchFI: A Runtime Perturbation Tool for DNNs'. Together they form a unique fingerprint.

Cite this