HackerPapers

arXiv:2101.07922cs.CV

LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition

Valeriia Cherepanova, Micah Goldblum, Harrison Foley, Shiyuan Duan, John Dickerson, Gavin Taylor, Tom Goldstein

Abstract

Facial recognition systems are increasingly deployed by private corporations, government agencies, and contractors for consumer services and mass surveillance programs alike. These systems are typically built by scraping social media profiles for user images. Adversarial perturbations have been proposed for bypassing facial recognition systems. However, existing methods fail on full-scale systems and commercial APIs. We develop our own adversarial filter that accounts for the entire image processing pipeline and is demonstrably effective against industrial-grade pipelines that include face detection and large scale databases. Additionally, we release an easy-to-use webtool that significantly degrades the accuracy of Amazon Rekognition and the Microsoft Azure Face Recognition API, reducing the accuracy of each to below 1%.

arXiv comments
Published as a conference paper at ICLR 2021
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition cs.CRCryptography and Security cs.LGMachine Learning

On Hacker News

Linked by 3 identifiable commenters in 3 comments across 3 threads, from Jan 2021 to Apr 2021.

Comments linking this paper, per year.

Discussed in comments3 threads

  1. Ask HN: Amyone successfully verify fawkes claims of protection against AI? 1 comment
  2. Adversarial.io – Fighting mass image recognition 1 comment

    • Folks interested in this kind of work should check out an upcoming ICLR paper, "LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition", from Tom Goldstein's group at Maryland. Similar pitch -- use a small adversarial perturbation to trick a…

      JohnPDickersonView on HNParent context

  3. LowKey web app tweaks images to thwart facial recognition systems 1 comment

    • Paper: LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition https://arxiv.org/abs/2101.07922

      samizdisView on HNParent context

Submitted to Hacker News

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