Adversarial attacks on medical machine learning

Adversarial attacks on medical machine learning. Finlayson, S. G; Bowers, J. D; Ito, J.; Zittrain, J. L; Beam*, A. L; and Kohane*, I. S Science, 363(6433):1287–1289, American Association for the Advancement of Science, 2019.

Paper abstract bibtex 8 downloads

With public and academic attention increasingly focused on the new role of machine learning in the health information economy, an unusual and no-longer-esoteric cat- egory of vulnerabilities in machine- learning systems could prove important. These vulnerabilities allow a small, carefully designed change in how inputs are presented to a system to completely alter its output, causing it to confidently arrive at manifestly wrong conclusions.

@article{finlayson2019adversarial,
  title={Adversarial attacks on medical machine learning},
  author={Finlayson, Samuel G and Bowers, John D and Ito, Joichi and Zittrain, Jonathan L and Beam*, Andrew L and Kohane*, Isaac S},
  journal={Science},
  volume={363},
  number={6433},
  pages={1287--1289},
  year={2019},
  abstract={With public and academic attention increasingly focused on the new role of machine learning in the health information economy, an unusual and no-longer-esoteric cat- egory of vulnerabilities in machine- learning systems could prove important. These vulnerabilities allow a small, carefully designed change in how inputs are presented to a system to completely alter its output, causing it to confidently arrive at manifestly wrong conclusions.},
  keywords={Deep Learning, Adversarial Attacks},
  url_Paper={https://www.dropbox.com/s/izimuap6762gfxe/finlayson_adversarial_science_2019.pdf?dl=1},
  publisher={American Association for the Advancement of Science}
}

Downloads: 8