Adversarial examples in the physical world · HackerPapers discussions

Adversarial examples in the physical world — mentioned by dijksterhuis

Wed, 22 Jul 2020 22:58:25 GMT

This can be thwarted fairly easily https://arxiv.org/pdf/1607.02533.pdf

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

Adversarial examples in the physical world — HN submission

Sat, 14 Sep 2019 13:28:36 GMT

Adverserial Examples in the Physical World

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

Adversarial examples in the physical world — mentioned by anishathalye

Thu, 02 Nov 2017 19:58:25 GMT

Goodfellow et al. demonstrate that adversarial misclassification works in the physical world: https://arxiv.org/abs/1607.02533 -- a printed image is consistently misclassified (demo here: https://www.youtube.com/watch?v=zQ_uMenoBCk) Recent work by me and some friends demonstrates that physical-world adversarial examples can actually be made quite robust, and you can synthesize 3D adversarial objects as well, and make them consistently classify as a desired target class: http://www.labsix.org/physical-objects-that-fool-neural-nets...

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

Adversarial examples in the physical world — HN submission

Mon, 01 Aug 2016 22:57:10 GMT

Adversarial examples in the physical world

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

Adversarial examples in the physical world — HN submission

Mon, 25 Jul 2016 13:39:01 GMT

Fooling machine learning image classifier

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

Adversarial examples in the physical world — mentioned by danielmorozoff

Sat, 23 Jul 2016 22:16:39 GMT

link to the paper. http://arxiv.org/abs/1607.02533 Their method more maximizing the cross entropy yields very peculiar results if you look at the images as the hyper-parameter iterations go up. It seems as if what we are seeing is some convolution with some peculiar form of noise. I wonder what the structure across these adversarial images looks like and whether it could provide some insight into certain patterns in cov net learning?

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

Adversarial examples in the physical world — HN submission

Thu, 14 Jul 2016 21:28:54 GMT

Adversarial Examples in the Real World

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

Adversarial examples in the physical world — HN submission

Wed, 13 Jul 2016 16:54:56 GMT

Adversarial examples in the physical world

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