Skip to the main content
icon-community

Medical AI systems could be vulnerable to adversarial attacks

With HMS and MIT faculty, Zittrain and Bowers co-author report in Science Journal

Medical AI systems could be vulnerable to adversarial attacks

A new paper published in Science by a team of researchers from Harvard University and MIT suggests that medical artificial intelligence systems could be vulnerable to adversarial attacks.

In their article, “Adversarial attacks on medical machine learning,” the authors note that medical machine-learning systems may be uniquely susceptible to such attacks because of the specific systems and incentives at play in the medical industry.

Read more in Harvard Law Today...

You might also like