cd /news/ai-safety/locality-sensitive-hashing-and-priva… · home topics ai-safety article
[ARTICLE · art-69524] src=arxiv.org ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Locality-Sensitive Hashing and Privacy

A new study by researchers (submitted on 27 Feb 2023) demonstrates that locality-sensitive hashing does not guarantee privacy, presenting attacks against Google's FLoC and the MinHash Hierarchy system. The attacks refute pre-image resistance, anonymity, and privacy claims, showing that for FLoC, 10% or more of browsing history can be reconstructed for 30% of users using Generative Adversarial Networks, and for MinHash, user movement can be limited to just 10% of the possible geographic area.

read2 min views1 publishedJul 23, 2026
Locality-Sensitive Hashing and Privacy
Image: source
[Submitted on 27 Feb 2023]


[View PDF](/pdf/2302.13635)

Abstract:Recently proposed systems aim at achieving privacy using locality-sensitive hashing. We show how these approaches fail by presenting attacks against two such systems: Google's FLoC proposal for privacy-preserving targeted advertising and the MinHash Hierarchy, a system for processing mobile users' traffic behavior in a privacy-preserving way. Our attacks refute the pre-image resistance, anonymity, and privacy guarantees claimed for these systems.

In the case of FLoC, we show how to deanonymize users using Sybil attacks and to reconstruct 10% or more of the browsing history for 30% of its users using Generative Adversarial Networks. We achieve this only analyzing the hashes used by FLoC. For MinHash, we precisely identify the movement of a subset of individuals and, on average, we can limit users' movement to just 10% of the possible geographic area, again using just the hashes. In addition, we refute their differential privacy claims.

References & Citations

...

Bibliographic Explorer

(What is the Explorer?) Connected Papers

(What is Connected Papers?) Litmaps

(What is Litmaps?) scite Smart Citations

(What are Smart Citations?)# Code, Data and Media Associated with this Article alphaXiv

(What is alphaXiv?) CatalyzeX Code Finder for Papers

(What is CatalyzeX?) DagsHub

(What is DagsHub?) Gotit.pub

(What is GotitPub?) Hugging Face

(What is Huggingface?) ScienceCast

(What is ScienceCast?)# Demos Influence Flower

(What are Influence Flowers?) CORE Recommender

(What is CORE?)# arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

── more in #ai-safety 4 stories · sorted by recency
── more on @google 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/locality-sensitive-h…] indexed:0 read:2min 2026-07-23 ·