Pith. sign in

REVIEW 4 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2101.07922 v2 pith:NLPS6QTE submitted 2021-01-20 cs.CV cs.CRcs.LG

Valeriia Cherepanova , Micah Goldblum , Harrison Foley , Shiyuan Duan , John Dickerson , Gavin Taylor , Tom Goldstein This is my paper
classification cs.CVcs.CRcs.LG
keywords recognitionsystemsadversarialfacialaccuracyfacemediasocial
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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%.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Adv-TGD: Adversarial Text-Guided Diffusion for Face Recognition Impersonation Attacks

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    Adv-TGD is a text-guided diffusion attack that achieves 85.9% black-box ASR on four face recognition models while preserving PSNR 28.18 dB and SSIM 0.981.

  2. AuraMask: An Extensible Pipeline for Developing Aesthetic Anti-Facial Recognition Image Filters

    cs.CV 2026-05 conditional novelty 7.0 of 10

    AuraMask produces 40 aesthetic anti-facial recognition filters that match or exceed prior adversarial effectiveness and achieve significantly higher user acceptance in a 630-person study.

  3. Personalized Face Privacy Protection From a Single Image

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    FaceCloak learns a lightweight identity-specific cloaking mask from a single image via synthetic face generation and iterative embedding perturbation to evade multiple recognition models.

  4. Challenges to Grassroots Organization Engagement with AI Policy

    cs.CY 2026-06 unverdicted novelty 3.0 of 10

    Case study of grassroots participatory design in US AI policymaking for marginalized communities, documenting engagement challenges and offering recommendations.

Pith tools