The Space of Transferable Adversarial Examples — mentioned by Sniffnoy

Fri, 19 May 2017 21:19:51 GMT

A note -- if you're linking to arXiv, it's better to link to the abstract (https://arxiv.org/abs/1704.03453) rather than directly to the PDF. From the abstract, one can easily click through to the PDF; not so the reverse. And the abstract allows one to do things like see different versions of the paper, search for other things by the same authors, etc. Thank you!

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

The Space of Transferable Adversarial Examples — mentioned by mholt

Fri, 19 May 2017 21:15:12 GMT

Since this blog post was written, the same authors have published further research on transferability which is what really makes these hard to defend against. They even present a proof of concept task that is resistant to transferring (although it is not super practical): https://arxiv.org/abs/1704.03453 If it interests anyone, I wrote up a bit about this and other threats related to machine learning models, a few weeks ago: https://matt.life/papers/security_privacy_neural_networks.pd...

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

The Space of Transferable Adversarial Examples · HackerPapers discussions

The Space of Transferable Adversarial Examples — mentioned by Sniffnoy

The Space of Transferable Adversarial Examples — mentioned by mholt