Skip to main content
ENHU
Home

Main navigation

  • Discover
    • News
    • Events
    • Tenders
  • Research fields
  • Resources
    • Publications
    • Downloads
    • Brochure
  • About us
  • Partners
  1. Home
  2. Publications
2021 International Joint Conference on Neural Networks (IJCNN)

Robust Classification Combined with Robust out-of-Distribution Detection: An Empirical Analysis

doi.org/10.1109/IJCNN52387.2021.9533635
Széchenyi Plusz RRF
Abstract

Recently, out-of-distribution (OOD) detection has received considerable attention, because confident labels assigned to OOD examples represent a vulnerability similar to adversarial input perturbation. We are interested in models that combine the benefits of being robust to adversarial input and being able to detect OOD examples. Furthermore, we require that both in-distribution classification and OOD detection be robust to adversarial input perturbation. Several related studies apply an ad-hoc combination of several design choices to achieve similar goals. One can use several functions over the logit or soft-max layer for defining training objectives, OOD detection methods and adversarial attacks. Here, we present a design-space that covers such design choices, as well as a principled way of evaluating the networks. This includes a strong attack scenario where both in-distribution and OOD examples are adversarially perturbed to mislead OOD detection. We draw several interesting conclusions based on our empirical analysis of this design space. Most importantly, we argue that the key factor is not the OOD training or detection method in itself, but rather the application of matching detection and training methods.

Authors
István Megyeri
István Hegedüs
Márk Jelasity
Institutes
Read more
Home

LinkedIn

Become a partner

Subscribe to newsletter

Send partnership request

Explore

  • News
  • Events
  • Tenders
  • Publications
  • Downloads
  • Partners

Research fields

  • Foundations of AI
  • Human Language Processing
  • Machine perception
  • Medical, Health and Biology
  • Security and Privacy
  • Sensors, IoT and Telecommunications

Contact us

Hungary, H-1111 Budapest,
Kende u. 13-17.
+36 1 279 6000
@email

© 2020-2021 Artifical Intelligence National Laboratory, Budapest