The DiCarlo Lab at MIT

  • People
  • Research
  • Publications
  • News
  • Courses
  • Brain Data
  • Join Us
  • Contact

Madry, Aleksander

  • 2022
    • Guo, Chong
    • Lee, Michael J.
    • Leclerc, Guillaume
    • Dapello, Joel
    • Rao, Yug
    • Madry, Aleksander
    • DiCarlo, James J.
    Adversarially trained neural representations may already be as robust as corresponding biological neural representations
    In:
    arXiv
    Available At:
    https://arxiv.org/abs/2206.11228v1
    Download file
    Abstract: Adversarially trained neural representations may already be as robust as corresponding biological neural representations

Massachusetts Institute of Technology
77 Massachusetts Avenue, Cambridge, MA, USA

Accessibility

McGovern Institute
Brain and Cognitive Sciences

Massachusetts Institute of Technology
Cambridge MA 02139-4307