---
res:
  bibo_abstract:
  - Adversarial training (i.e., training on adversarially perturbed input data) is
    a well-studied method for making neural networks robust to potential adversarial
    attacks during inference. However, the improved robustness does not come for free
    but rather is accompanied by a decrease in overall model accuracy and performance.
    Recent work has shown that, in practical robot learning applications, the effects
    of adversarial training do not pose a fair trade-off but inflict a net loss when
    measured in holistic robot performance. This work revisits the robustness-accuracy
    trade-off in robot learning by systematically analyzing if recent advances in
    robust training methods and theory in conjunction with adversarial robot learning,
    are capable of making adversarial training suitable for real-world robot applications.
    We evaluate three different robot learning tasks ranging from autonomous driving
    in a high-fidelity environment amenable to sim-to-real deployment to mobile robot
    navigation and gesture recognition. Our results demonstrate that, while these
    techniques make incremental improvements on the trade-off on a relative scale,
    the negative impact on the nominal accuracy caused by adversarial training still
    outweighs the improved robustness by an order of magnitude. We conclude that although
    progress is happening, further advances in robust learning methods are necessary
    before they can benefit robot learning tasks in practice.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Mathias
      foaf_name: Lechner, Mathias
      foaf_surname: Lechner
      foaf_workInfoHomepage: http://www.librecat.org/personId=3DC22916-F248-11E8-B48F-1D18A9856A87
  - foaf_Person:
      foaf_givenName: Alexander
      foaf_name: Amini, Alexander
      foaf_surname: Amini
  - foaf_Person:
      foaf_givenName: Daniela
      foaf_name: Rus, Daniela
      foaf_surname: Rus
  - foaf_Person:
      foaf_givenName: Thomas A
      foaf_name: Henzinger, Thomas A
      foaf_surname: Henzinger
      foaf_workInfoHomepage: http://www.librecat.org/personId=40876CD8-F248-11E8-B48F-1D18A9856A87
    orcid: 0000-0002-2985-7724
  bibo_doi: 10.1109/LRA.2023.3240930
  bibo_issue: '3'
  bibo_volume: 8
  dct_date: 2023^xs_gYear
  dct_identifier:
  - UT:000936534100012
  dct_isPartOf:
  - http://id.crossref.org/issn/2377-3766
  dct_language: eng
  dct_publisher: Institute of Electrical and Electronics Engineers@
  dct_title: Revisiting the adversarial robustness-accuracy tradeoff in robot learning@
...