HackerPapers

arXiv:1712.09665cs.CV

Adversarial Patch

Tom B. Brown, Dandelion Mané, Aurko Roy, Martín Abadi, Justin Gilmer

Abstract

We present a method to create universal, robust, targeted adversarial image patches in the real world. The patches are universal because they can be used to attack any scene, robust because they work under a wide variety of transformations, and targeted because they can cause a classifier to output any target class. These adversarial patches can be printed, added to any scene, photographed, and presented to image classifiers; even when the patches are small, they cause the classifiers to ignore the other items in the scene and report a chosen target class. To reproduce the results from the paper, our code is available at https://github.com/tensorflow/cleverhans/tree/master/examples/adversarial_patch

arXiv comments
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition

On Hacker News

Linked by 5 identifiable commenters in 5 comments across 5 threads, from May 2018 to Mar 2024. Found in 6 HN submissions from Dec 2017 to Feb 2026. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments5 threads

  1. The Elements of Differentiable Programming 1 comment

    • Yes, these are “adversarial patches” in image classification, like https://arxiv.org/abs/1712.09665 . Similarly you can take these adversaries and add them to your own larger model, in an arms race.

      lsbView on HNParent context

  2. Some shirts hide you from cameras, but will anyone wear them? 1 comment

    • Honestly, I'd wear that dress easily, even for regular outings, not just for hiding from cameras. Those hoodies, though, maybe I'm an old fart but they're a bit too "abstract". Sadly, those seem like the most effective option right now. I read the Adversarial Patch article [0]…

      BelleOfTheBallView on HNParent context

  3. How to be anonymous in the age of surveillance 1 comment

    • The article mentions the use of "Juggalo" style face paint to avoid face detection. This type of countermeasure is effective against conventional HOG-SVM type face detectors such as [1], but would be inadvisable for daily use. To deal with more advanced convolutional detectors…

      lwnealView on HNParent context

  4. Testing Robustness Against Unforeseen Adversaries 1 comment

    • For better or worse, this helps establish neural networks that are not (or less?) vulnerable to deception via e.g. fake eyeglasses [ LINK: https://dl.acm.org/citation.cfm?id=2978392 ] and adversarial stickers [ LINK: https://arxiv.org/abs/1712.09665 ]. From the post: "We’ve…

      mrkootView on HNParent context

  5. Thanks to facial recognition, a third person is arrested following a pop concert 1 comment

    • Masks, face altering, stickers, etc. I like this research about "Adversarial Patches" - stickers that confuse image recognition systems. I imagine one may wear a display with ever changing images that are salient and confuse such systems. > Research Article…

      dpflanView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.