Adversarial Examples that Fool both Computer Vision and Time-Limited Humans · HackerPapers discussions

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans — mentioned by ben_w

Thu, 03 Nov 2022 21:33:46 GMT

22 May 2018: https://arxiv.org/abs/1802.08195

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

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans — mentioned by katmannthree

Wed, 12 May 2021 22:13:15 GMT

I find these types of things to be a lot more interesting as well. With respect the behavioral modifiers I feel like they really help explain how societies actually function, once you start paying attention you see just how effective and pervasive they really are. This study[0] discusses adversarial images which fool both ML classifiers and time limited humans, a rather interesting development in the field. It's a good space to keep an eye on in general, at some point someone's probably going to discover a snowcrash-level informational hazard and it would be nice to have some warning. [0]…

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

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans — mentioned by dontreact

Mon, 12 Nov 2018 06:25:01 GMT

https://arxiv.org/pdf/1802.08195.pdf Looks like we are starting to find examples. I think your intuition is wrong because humans are adapted to what exists naturally so of course there are no naturally occurring adversarial examples. It seems like the same is true for models trained on large natural image sets though. My point is not wow let’s stop developing neural networks they are perfect. It’s more let’s go collect real world test sets to find and then fix gaps. Adversarial examples actually help very little in making nets more robust in the ways that matter.

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

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans — HN submission

Sun, 11 Nov 2018 08:29:40 GMT

Adversarial Examples That Fool Both Computer Vision and Time-Limited Humans

120 points; 37 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans — mentioned by ben_w

Wed, 07 Nov 2018 08:02:12 GMT

Recent update — we do know, and humans are vulnerable to perturbations created to fool a multitude of existing AI: https://arxiv.org/pdf/1802.08195.pdf

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

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans — HN submission

Wed, 21 Mar 2018 07:54:05 GMT

Adversarial Examples That Fool Both Human and Computer Vision

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

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans — mentioned by isp

Fri, 02 Mar 2018 10:37:57 GMT

PDF: https://arxiv.org/pdf/1802.08195.pdf Figure 1 - an image of a cat, adversarially perturbed to look like a dog.

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

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans — HN submission

Fri, 02 Mar 2018 10:37:07 GMT

Adversarial Examples That Fool Both Human and Computer Vision

3 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans — HN submission

Fri, 23 Feb 2018 02:05:09 GMT

Adversarial Examples That Fool Both Human and Computer Vision

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