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, & Kohane*, I. S Science, 363(6433):1287–1289, American Association for the Advancement of Science, 2019.

Paper abstract bibtex 17 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: 17

{"_id":"DbXR47hirtP7CaKTJ","bibbaseid":"finlayson-bowers-ito-zittrain-beam-kohane-adversarialattacksonmedicalmachinelearning-2019","authorIDs":[],"author_short":["Finlayson, S. G","Bowers, J. D","Ito, J.","Zittrain, J. L","Beam*, A. L","Kohane*, I. S"],"bibdata":{"bibtype":"article","type":"article","title":"Adversarial attacks on medical machine learning","author":[{"propositions":[],"lastnames":["Finlayson"],"firstnames":["Samuel","G"],"suffixes":[]},{"propositions":[],"lastnames":["Bowers"],"firstnames":["John","D"],"suffixes":[]},{"propositions":[],"lastnames":["Ito"],"firstnames":["Joichi"],"suffixes":[]},{"propositions":[],"lastnames":["Zittrain"],"firstnames":["Jonathan","L"],"suffixes":[]},{"propositions":[],"lastnames":["Beam*"],"firstnames":["Andrew","L"],"suffixes":[]},{"propositions":[],"lastnames":["Kohane*"],"firstnames":["Isaac","S"],"suffixes":[]}],"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","bibtex":"@article{finlayson2019adversarial,\n title={Adversarial attacks on medical machine learning},\n author={Finlayson, Samuel G and Bowers, John D and Ito, Joichi and Zittrain, Jonathan L and Beam*, Andrew L and Kohane*, Isaac S},\n journal={Science},\n volume={363},\n number={6433},\n pages={1287--1289},\n year={2019},\n 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.},\n keywords={Deep Learning, Adversarial Attacks},\n url_Paper={https://www.dropbox.com/s/izimuap6762gfxe/finlayson_adversarial_science_2019.pdf?dl=1},\n publisher={American Association for the Advancement of Science}\n}\n\n","author_short":["Finlayson, S. G","Bowers, J. D","Ito, J.","Zittrain, J. L","Beam*, A. L","Kohane*, I. S"],"key":"finlayson2019adversarial","id":"finlayson2019adversarial","bibbaseid":"finlayson-bowers-ito-zittrain-beam-kohane-adversarialattacksonmedicalmachinelearning-2019","role":"author","urls":{" paper":"https://www.dropbox.com/s/izimuap6762gfxe/finlayson_adversarial_science_2019.pdf?dl=1"},"keyword":["Deep Learning","Adversarial Attacks"],"metadata":{"authorlinks":{}},"downloads":17,"html":""},"bibtype":"article","biburl":"https://www.dropbox.com/s/0k6pa735xx3gr9i/citations.txt?dl=1","creationDate":"2019-07-24T12:46:58.187Z","downloads":17,"keywords":["deep learning","adversarial attacks"],"search_terms":["adversarial","attacks","medical","machine","learning","finlayson","bowers","ito","zittrain","beam*","kohane*"],"title":"Adversarial attacks on medical machine learning","year":2019,"dataSources":["2LQLmS62hSLmYBK2a","R7XXNLtmcExJiuMoA"]}