Adversarial attacks on medical machine learning.
Adversarial attacks on medical machine learning.
复制标题
DOI：
10.1126/science.aaw4399
复制
发表时间：
2019-03-22
期刊：
影响因子：
--
通讯作者：
Kohane IS
中科院分区：
文献类型：
--
作者：
Finlayson SG;Bowers JD;Ito J;Zittrain JL;Beam AL;Kohane IS
随着公众和学术界越来越多地关注机器学习在医疗信息经济中的新角色，机器学习系统中一类不同寻常且不再深奥的漏洞可能会被证明是重要的。这些漏洞允许对输入提供给系统的方式进行精心设计的微小更改，以完全改变系统的输出，导致系统自信地得出明显错误的结论。到目前为止，这些颠覆原本可靠的机器学习系统的先进技术--所谓的对抗性攻击--主要是计算机科学研究人员感兴趣的。然而，医疗保健内部经常相互竞争的利益格局，以及系统产出中数十亿美元的利害关系，意味着相当大的问题。我们概述了医疗保健系统中的各种参与者可能不得不使用对抗性攻击的动机，并开始讨论如何应对它们。我们不仅没有阻止医学机器学习的持续创新，还呼吁医学、技术、法律和伦理专家积极参与，追求机器学习将实现的高效、广泛和有效的医疗保健。
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 category 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. These advanced techniques to subvert otherwise-reliable machine-learning systems—so-called adversarial attacks—have, to date, been of interest primarily to computer science researchers (1). However, the landscape of often-competing interests within health care, and billions of dollars at stake in systems' outputs, implies considerable problems. We outline motivations that various players in the health care system may have to use adversarial attacks and begin a discussion of what to do about them. Far from discouraging continued innovation with medical machine learning, we call for active engagement of medical, technical, legal, and ethical experts in pursuit of efficient, broadly available, and effective health care that machine learning will enable.
登录
查看更多内容
影响因子：
1.5
作者：
SALTZER, JH;REED, DP;CLARK, DD
通讯作者：
CLARK, DD
影响因子：
120.7
作者：
Wynia, MK;Cummins, DS;Wilson, IB
通讯作者：
Wilson, IB
影响因子：
13.8
作者：
Sun, Eric C.;Dutton, Richard P.;Jena, Anupam B.
通讯作者：
Jena, Anupam B.
影响因子：
8
作者：
Biggio, Battista;Roli, Fabio
通讯作者：
Roli, Fabio
DOI：
10.1098/rsif.2017.0387
发表时间：
2018-04
期刊：
Journal of the Royal Society, Interface
影响因子：
--
作者：
Ching T;Himmelstein DS;Beaulieu-Jones BK;Kalinin AA;Do BT;Way GP;Ferrero E;Agapow PM;Zietz M;Hoffman MM;Xie W;Rosen GL;Lengerich BJ;Israeli J;Lanchantin J;Woloszynek S;Carpenter AE;Shrikumar A;Xu J;Cofer EM;Lavender CA;Turaga SC;Alexandari AM;Lu Z;Harris DJ;DeCaprio D;Qi Y;Kundaje A;Peng Y;Wiley LK;Segler MHS;Boca SM;Swamidass SJ;Huang A;Gitter A;Greene CS
通讯作者：
Greene CS