TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Universal adversarial perturbations

108 pointsby legatusover 8 years ago

16 comments

legatusover 8 years ago
Abstract: Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic algorithm for computing universal perturbations, and show that state-of-the-art deep neural networks are highly vulnerable to such perturbations, albeit being quasi-imperceptible to the human eye. We further empirically analyze these universal perturbations and show, in particular, that they generalize very well across neural networks. The surprising existence of universal perturbations reveals important geometric correlations among the high-dimensional decision boundary of classifiers. It further outlines potential security breaches with the existence of single directions in the input space that adversaries can possibly exploit to break a classifier on most natural images.
评论 #12824898 未加载
danbrucover 8 years ago
This seems to imply the features lernt by neural networks are very different from the features humans use to distinguish the same objects because they are affected by distortions that do almost not interfere with features used by humans at all.
评论 #12828177 未加载
评论 #12829039 未加载
thisisdaveover 8 years ago
Several of the universal perturbation vectors in Figure 4 remind me a lot of Deep Dream&#x27;s textures.<p>I wonder what it is about these high-saturation, stripy-spiraly bits that these networks are responding to.<p>Is it something inherent in natural images? In the training algorithm? In our image compression algorithms? Presumably, the networks would work better if they weren&#x27;t so hypersensitive to these patterns, so finding a way to dial that down seems like it could be pretty fruitful.
评论 #12827327 未加载
pfortunyover 8 years ago
This is really great research and interesting: (very roughly) how to compute a very small mask which, when applied to any image, makes the neural network misclassify it, whereas humans would notice no essential difference.<p>Quite remarkable.
评论 #12825537 未加载
dkarapetyanover 8 years ago
This is why I&#x27;m never driving a car that is classifying stuff with neural networks. Some dust, some shitty weather conditions and that pigeon becomes a green light.
评论 #12826541 未加载
评论 #12829887 未加载
jmountover 8 years ago
In signal processing you often have to pass the data through some sort of low-pass filter before attempting your analysis. I would be surprised if that isn&#x27;t one of the methods being tried to protect deep neural nets from some of these attacks. Obviously there are some issues (needing to train on similar data, and such blurring interfering with first-level features that emulate edge-detection and so on).
nullcover 8 years ago
So what happens when you stick this procedure in the training loop? Do you get networks which are robust against doubly-universal perturbations?
dTalover 8 years ago
What happens if you include the perturbations in your training data?
评论 #12825303 未加载
jonathanycover 8 years ago
Reminds me a little bit of the short story BLIT [1], where scientists have accidentally created images that crash the human brain. Cool stuff!<p>[1]: <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;BLIT_(short_story)" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;BLIT_(short_story)</a>
评论 #12828290 未加载
评论 #12828291 未加载
amiramirover 8 years ago
I&#x27;m guessing it won&#x27;t be long until someone uses this technique to computer and apply perturbation masks to pornographic imagery and make NN-based porn detectors&#x2F;filters (like the one Yahoo recently open-sourced) a lot less effective.
yodonover 8 years ago
Is there reason to think the human visual system is sufficiently well modeled by deep neural nets that our brains might exhibit this same behavior? My first thought was the perturbation images would need to be distinct per person, but photosensitive epilepsy like the Pokémon event [0] might suggest the possibility of shared perturbation vectors.<p>[0] <a href="https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;Photosensitive_epilepsy" rel="nofollow">https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;Photosensitive_epilepsy</a>
评论 #12825814 未加载
评论 #12825633 未加载
javajoshover 8 years ago
My science-fiction brain is, of course, interested in this as a method to defeat face-detection <i>in a way humans can&#x27;t see</i>. I&#x27;d like to think that the crew of the Firefly used this technology to avoid detection when they did jobs in the heart of Alliance territory.
oh_sighover 8 years ago
Could you just add noise to any image before passing it through a NN to defeat this kind of attack?
yodonover 8 years ago
Can someone help with a notation question? In section 4 of the paper, the norm of the perturbation is constrained to a maximum of 2&#x27;000 which presumably is &quot;small&quot; but I don&#x27;t know how to parse an apostrophe like that
评论 #12825497 未加载
bmh100over 8 years ago
My intuition is that the existence of adversarial images with barely perceptible differences but a high-confidence misclassification will lead to a new NN architecture for image classification.
mathgeniusover 8 years ago
This is like Godel incompleteness for deep learning.
评论 #12828509 未加载