Privacy-Preserving Representations are not Enough: Recovering Scene Content from Camera Poses

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00371977" target="_blank" >RIV/68407700:21230/23:00371977 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/23:00371977

Výsledek na webu

<a href="https://doi.org/10.1109/CVPR52729.2023.01262" target="_blank" >https://doi.org/10.1109/CVPR52729.2023.01262</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR52729.2023.01262" target="_blank" >10.1109/CVPR52729.2023.01262</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Privacy-Preserving Representations are not Enough: Recovering Scene Content from Camera Poses

Popis výsledku v původním jazyce

Visual localization is the task of estimating the camera pose from which a given image was taken and is central to several 3D computer vision applications. With the rapid growth in the popularity of AR/VR/MR devices and cloud based applications, privacy issues are becoming a very im portant aspect of the localization process. Existing work on privacy-preserving localization aims to defend against an attacker who has access to a cloud-based service. In this paper, we show that an attacker can learn about details of a scene without any access by simply querying a localization service. The attack is based on the observation that modern visual localization algorithms are robust to variations in ap pearance and geometry. While this is in general a desired property, it also leads to algorithms localizing objects that are similar enough to those present in a scene. An attacker can thus query a server with a large enough set of images of objects, e.g., obtained from the Internet, and some of them will be localized. The attacker can thus learn about object placements from the camera poses returned by the service (which is the minimal information returned by such a ser vice). In this paper, we develop a proof-of-concept version of this attack and demonstrate its practical feasibility. The attack does not place any requirements on the localization algorithm used, and thus also applies to privacy-preserving representations. Current work on privacy-preserving repre sentations alone is thus insufficient.

Název v anglickém jazyce

Privacy-Preserving Representations are not Enough: Recovering Scene Content from Camera Poses

Popis výsledku anglicky

Visual localization is the task of estimating the camera pose from which a given image was taken and is central to several 3D computer vision applications. With the rapid growth in the popularity of AR/VR/MR devices and cloud based applications, privacy issues are becoming a very im portant aspect of the localization process. Existing work on privacy-preserving localization aims to defend against an attacker who has access to a cloud-based service. In this paper, we show that an attacker can learn about details of a scene without any access by simply querying a localization service. The attack is based on the observation that modern visual localization algorithms are robust to variations in ap pearance and geometry. While this is in general a desired property, it also leads to algorithms localizing objects that are similar enough to those present in a scene. An attacker can thus query a server with a large enough set of images of objects, e.g., obtained from the Internet, and some of them will be localized. The attacker can thus learn about object placements from the camera poses returned by the service (which is the minimal information returned by such a ser vice). In this paper, we develop a proof-of-concept version of this attack and demonstrate its practical feasibility. The attack does not place any requirements on the localization algorithm used, and thus also applies to privacy-preserving representations. Current work on privacy-preserving repre sentations alone is thus insufficient.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

ISBN

979-8-3503-0129-8

ISSN

1063-6919

e-ISSN

2575-7075

Počet stran výsledku

10

Strana od-do

13132-13141

Název nakladatele

IEEE Computer Society

Místo vydání

USA

Místo konání akce

Vancouver

Datum konání akce

18. 6. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001062522105043