Events at The University of Manchester
  • University home
  • Events
  • Home
  • Exhibitions
  • Conferences
  • Lectures and seminars
  • Performances
  • Events for prospective students
  • Family events
  • All Events

Computer Science Research Talk: : Exposing Previously Undetectable Faults in Deep Neural Networks

Dates:5 May 2021
Times:14:00 - 15:00
What is it:Seminar
Organiser:Department of Computer Science
Who is it for:University staff, Adults, Current University students
Speaker:Isaac Dunn
See travel and contact information
Add to your calendar

More information

  • Computer Science Research Talk

Other events

  • In category "Seminar"
  • In group "(CS) Computer Science seminar series"
  • In group "(CS) Intelligent systems"
  • By Department of Computer Science

You are welcome to the forthcoming Research Talk in Computer Science (online)

Joining details:

Join Zoom Meeting https://zoom.us/j/91635482399

Speaker: Isaac Dunn Host: Dr Lucas Cordeiro

Title: Exposing Previously Undetectable Faults in Deep Neural Networks

Abstract: Existing methods for testing DNNs solve the oracle problem by constraining the raw features (e.g. image pixel values) to be within a small distance of a dataset example for which the desired DNN output is known. But this limits the kinds of faults these approaches are able to detect. In this paper, we introduce a novel DNN testing method that is able to find faults in DNNs that other methods cannot. The crux is that, by leveraging generative machine learning, we can generate fresh test cases that vary in their high-level features (for images, these include object shape, location, texture, and colour). We demonstrate that our approach is capable of detecting deliberately injected faults as well as new faults in state-of-the-art DNNs, and that in both cases, existing methods are unable to find these faults.

Bio: Isaac Dunn is a PhD candidate (third year) at the University of Oxford. Their research focuses on improving our understanding of limitations in current machine learning models, with a view to making improvements and working towards genuinely trustworthy ML systems.

Speaker

Isaac Dunn

Role: PhD student

Organisation: Department of Computer Science

Travel and Contact Information

Find event

https://zoom.us/j/91635482399

Contact event

Lucas Cordeiro

lucas.cordeiro@manchester.ac.uk

Share / follow event

Contact us

  • +44 (0) 161 306 6000

Find us

The University of Manchester
Oxford Rd
Manchester
M13 9PL
UK

Connect with the University

  • Facebook page for The University of Manchester
  • Twitter page for The University of Manchester
  • YouTube page for The University of Manchester
  • Google+ page for The University of Manchester
  • Pinterest page for The University of Manchester

  • Privacy /
  • Copyright notice /
  • Accessibility /
  • Freedom of information /
  • Charitable status /
  • Royal Charter Number: RC000797
  • Close menu
  • Home
    • Featured events
    • Today's events
    • The Whitworth events
    • Manchester Museum events
    • Jodrell Bank Discovery Centre events
    • Martin Harris Centre events
    • The John Rylands Library events
    • Exhibitions
    • Conferences
    • Lectures and seminars
    • Performances
    • Events for prospective students
    • Family events
    • All events