Adversarial Attacks Against Medical Deep Learning Systems · HackerPapers discussions

Adversarial Attacks Against Medical Deep Learning Systems — mentioned by applecrazy

Tue, 22 Oct 2019 19:51:48 GMT

> ML for healthcare. I'm kind of apprehensive about this advancement. There's many ways to mess this up, from intentional dataset poisoning (to encourage patients to get unnecessary procedure) to just terrible errors made with just a shift in data capture methodology. This paper has a lot of detail on how such systems can fail (https://arxiv.org/pdf/1804.05296.pdf).

Paper and discussion history. A mention is not an endorsement.

Adversarial Attacks Against Medical Deep Learning Systems — HN submission

Sun, 22 Apr 2018 20:07:23 GMT

Adversarial Attacks Against Medical Deep Learning Systems [pdf]

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Adversarial Attacks Against Medical Deep Learning Systems — HN submission

Tue, 17 Apr 2018 17:38:43 GMT

Adversarial Attacks Against Medical Deep Learning Systems

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.