Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images · HackerPapers discussions

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by penagwin

Wed, 26 Jun 2019 21:52:47 GMT

It will always be a game of cat and mouse. Even with Neural networks involved :D. [0] https://arxiv.org/abs/1412.1897 [1] https://arxiv.org/abs/1710.08864

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by ktta

Tue, 12 Sep 2017 19:38:53 GMT

There is a different way to trick neural networks. https://arxiv.org/abs/1412.1897

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by ogdan

Sat, 15 Jul 2017 02:05:43 GMT

For some background, see https://arxiv.org/pdf/1412.1897.pdf which has some cool visuals of pictures that make neural networks to strange things. Looks like this group might have solved adversarial examples (or rather, found that they're not a problem in practice after all) for self driving cars! Yann LeCun seems confident about it: https://mobile.twitter.com/ylecun/status/885384106418294784

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by jxcole

Fri, 14 Apr 2017 19:57:45 GMT

TLDR: The point is to correct a known flaw with image recognition algorithms. I'm not a professional researcher, but here's what I gather from reading other articles: One major problem with image recognition in machines is that while they are generally able to recognize real images correctly, they are 1) Easily fooled 2) Unable to have human-type image understanding. For example, you can recognize an animated character as a human, even though you may never have seen that particular style of drawing before. One major problem that people realized is that deep neural networks have a tendency to…

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by jsprogrammer

Fri, 28 Oct 2016 14:52:22 GMT

NNs/ANNs/DNNs/xNNs have already[0] been framed as easily fooled. [0] https://arxiv.org/pdf/1412.1897.pdf

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by re

Sat, 01 Oct 2016 02:36:39 GMT

> I don't understand how Google's algorithm can be misled into finding sexiness in those. I'm reminded of a paper for which the authors generated different pictures of static that fooled neural network image classifiers into confidently identifying them as different objects: https://arxiv.org/abs/1412.1897 Wired summary: https://www.wired.com/2015/01/simple-pictures-state-art-ai-s... > Computer vision and human vision are nothing alike. And yet, since it increasingly relies on neural networks that teach themselves to see, we’re not sure precisely how computer vision differs from our own. As…

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by aficionado

Sat, 11 Jun 2016 21:52:07 GMT

Basically this video ignores the history of machine learning in general. Jumping from Expert Systems to Neural Networks and Deep Learning is actually ignoring 36 years (and billions of dollars) of research http://machinelearning.org/icml.html (Breiman, Quinlan, Mitchell, Dietterich, Domingos, etc). Calling 2012 the seminal moment of Deep Learning is quite hard to digest. Maybe it means that 2012 is the point in time when the VC community discovered machine learning? Even harder to digest is calling Deep Learning the most productive and accurate machine learning system. What about more…

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by feelix

Sun, 05 Jun 2016 03:15:34 GMT

That's a good point and it also brings to mind a way to fight it. This http://arxiv.org/pdf/1412.1897v4.pdf could be one way. You could generate images which are not of someone who wants to protect his privacy, but tweak them to strongly correlate to an image of that person by the neural net, whereas it could be a picture of anything you have just optimized (the images could be just noise, or another person, etc). You could generate batches of those and upload them, and confirm to Facebook that they are indeed photos of the person who wants their privacy back. You could repeat this…

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by discardorama

Mon, 23 May 2016 02:46:40 GMT

> given that we now have programs that look at a photograph and say "Women wearing a hat, sitting on a bar stool and drinking wine" That may be; but then there's also this: http://arxiv.org/abs/1412.1897

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by jkldotio

Mon, 01 Feb 2016 06:21:11 GMT

I find it less interesting in terms of applications. I am sure finding the causes of these illusions will help in understanding aspects of how the system, human or machine, subject to the illusion operates; however, so many of them depend on either a static image or a fixed perspective that it just doesn't seem to be all that big of an issue to me. The visual illusions humans are subject to are frequently defeated by some simple motion to reposition the viewer and there seem to be few illusions that can sustain being in motion themselves and still fool people. From that it doesn't seem all…

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by ankurdhama

Mon, 09 Nov 2015 04:53:34 GMT

If DNN are so smart then why they can be easily fooled: http://arxiv.org/abs/1412.1897

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by jhundal

Sat, 20 Jun 2015 18:14:54 GMT

Definitely agree here, want to add a link to this paper which shows how far we still have to go (and questions whether the current models will ever replicate human vision): http://arxiv.org/abs/1412.1897

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by jyzzmoe

Sat, 13 Jun 2015 02:36:01 GMT

And yet ... http://arxiv.org/pdf/1412.1897v1.pdf%EF%BB%BF

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by cafebeen

Fri, 12 Jun 2015 15:12:05 GMT

It's entirely possible for biometrics to spoofed. For example, folks have already figured out how to trick deep neural nets: http://arxiv.org/abs/1412.1897 Not to mention bio-engineering possibilities on the horizon. Of course, just because we can use a certain technology doesn't mean we should...

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by yummyfajitas

Mon, 16 Mar 2015 14:47:01 GMT

Algorithmic biases often reflect human biases I've been doing this for a while and I've literally never met a human who told an algorithm to overweight x[23] ("good looking"), x[48] ("is white") and x[873] ("is wealthy"), for x a 1,100-dimensional feature vector. Algorithms do have biases, but they are almost always orthogonal to the human ones. Witness, for example, all the recent "we can fool deep learning image recognition systems" papers. http://arxiv.org/abs/1412.1897 http://arxiv.org/abs/1312.6199 At this point I'm 90% sure you are a layperson who's never actually programmed such a…

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by HCIdivision17

Tue, 30 Dec 2014 21:00:31 GMT

In (2)'s paper [2], the images are really neat. Staring at it for a few moments, I feel like I can see where the computer is coming from. A bit. The robin, armadillo, centipede, peacock, and bubble all actually have a little swirl of features that - to me at least - resemble the labels provided. But from afar, and you've got to basically damp the noise. I did this by taking my glasses off and leaning about 8 inches from the screen (with the grid taking about 3 inches wide). I've got about -7.5 diopter near-sightedness, so this cleaned the images right up. At least the armadillo I would have…

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — HN submission

Thu, 11 Dec 2014 01:23:10 GMT

Deep Neural Networks Are Easily Fooled [pdf]

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — mentioned by simonster

Tue, 09 Dec 2014 21:03:49 GMT

Automatic feature choice can actually lead to a set of features that resembles V1 receptive fields (as demonstrated by Olshausen and Field in https://courses.cs.washington.edu/courses/cse528/11sp/Olshau...). I recently attended a talk by Geoff Hinton on "capsules." He pointed out that the max pooling used in convolutional neural networks effectively disregards information about relationships among features. Instead, he propose a network composed of "capsules" that each estimate whether an implicitly defined intermediate feature is present and its pose. The idea is that an object is present…

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

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images — HN submission

Tue, 09 Dec 2014 08:20:00 GMT

Deep Neural Networks Are Easily Fooled

183 points; 60 discussion replies on HN. Paper and source history. A submission is not an endorsement.