Universal adversarial perturbations · HackerPapers discussions

Universal adversarial perturbations — mentioned by zkms

Mon, 12 Nov 2018 06:39:21 GMT

Speaking of similarity between CV and human visual systems; it was kinda striking to me just how psychedelic/"trippy" the "universal adversarial perturbations" (see page 5 in https://arxiv.org/pdf/1610.08401.pdf) look. Indeed, the look of visual hallucination "form constants" is intimately related to the machinery in the visual cortex that detects edges/contours/surfaces: https://www.math.uh.edu/~dynamics/reprints/papers/nc.pdf and such visual hallucinations can be elicited without any drugs or physiological interventions/defects -- just via diffuse flickering light…

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

Universal adversarial perturbations — mentioned by Donald

Sun, 29 Oct 2017 05:17:07 GMT

See https://arxiv.org/abs/1610.08401 for model agnostic examples of adversarial attacks.

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

Universal adversarial perturbations — mentioned by yorwba

Fri, 27 Oct 2017 13:42:55 GMT

Actually, no [1]. From the abstract: We can cause the network to misclassify an image by applying a certain imperceptible perturbation, which is found by maximizing the network's prediction error. In addition, the specific nature of these perturbations is not a random artifact of learning: the same perturbation can cause a different network, that was trained on a different subset of the dataset, to misclassify the same input. [1] https://arxiv.org/abs/1312.6199 EDIT: Also interesting: "Universal Adversarial Perturbations" https://arxiv.org/abs/1610.08401

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

Universal adversarial perturbations — mentioned by clickok

Tue, 18 Jul 2017 07:19:39 GMT

I am unsure what you mean-- do you mean with different training sets but the same testing set? It's an interesting question; maybe the reason for (some) of these adversarial vulnerabilities is due to a handful of bad training examples. You could formulate it as a search problem to see if there's particular images (or small groups of images) that are responsible for the adversarial vulnerabilities. This might then indicate that some of these perturbations are really just taking advantage of the fact that neural nets tend to "memorize" some of the data, so we're not really exploiting some deep…

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

Universal adversarial perturbations — mentioned by zkms

Sat, 03 Jun 2017 02:33:36 GMT

This reminds me of those blinky goggles that made you see a bunch of trippy patterns (even though the blinkiness was completely diffuse!), here's the instructions (http://wealoneonearth.blogspot.com/2009/09/how-to-build-gogg...) and here's a proper scientific paper about this phenomenon: http://journals.plos.org/ploscompbiol/article?id=10.1371/jou... . The interesting thing is that the patterns that recur (known as "form constants, https://en.wikipedia.org/wiki/Form_constant ) in these geometric visual hallucinations are pretty similar to those obtained by taking hallucinogenic drugs (like…

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

Universal adversarial perturbations — mentioned by vicaya

Thu, 12 Jan 2017 23:57:51 GMT

This is obviously data dependent. I suspect that the advantage of human is much higher in colloquial content vs written (esp. news) content. "Universal Adversarial Perturbations"[1] last year showed that you can easily generate reasonable (to human) perturbations to completely fool the state of the art DNNs for images. I suspect that the same is true for the current batch of NMTs as well. As a simple demo, I change the example Chinese a little (就要下班了。下班了再说吧。Only aux characters changes with the same meaning) and all NMTs failed spectacularly in different ways. Google: It is necessary to get…

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

Universal adversarial perturbations — mentioned by taliesinb

Mon, 14 Nov 2016 16:15:27 GMT

https://arxiv.org/pdf/1610.08401v1.pdf Sorry, I have to ask.. any relation to Dan Fortunato? Maybe that's just a really common name in Boston.

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

Universal adversarial perturbations — mentioned by oifnwoivnoinvo

Sun, 13 Nov 2016 17:09:52 GMT

"Generative models are only vulnerable to adversarial examples that are actually unlikely in the data distribution. They do not have patterns or filters that can be added to ordinary images to cause wild misclassifications." ^ Actually, you are wrong on this. See this recent paper "Universal adversarial perturbations" https://arxiv.org/pdf/1610.08401v1.pdf

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

Universal adversarial perturbations — HN submission

Sat, 29 Oct 2016 15:35:03 GMT

Universal adversarial perturbations

108 points; 46 discussion replies on HN. Paper and source history. A submission is not an endorsement.