English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Visual localization is the task of estimating the camera pose from which agiven image was taken and is central to several 3D computer visionapplications. With the rapid growth in the popularity of AR/VR/MR devices andcloud-based applications, privacy issues are becoming a very important aspectof the localization process. Existing work on privacy-preserving localizationaims to defend against an attacker who has access to a cloud-based service. Inthis paper, we show that an attacker can learn about details of a scene withoutany access by simply querying a localization service. The attack is based onthe observation that modern visual localization algorithms are robust tovariations in appearance and geometry. While this is in general a desiredproperty, it also leads to algorithms localizing objects that are similarenough to those present in a scene. An attacker can thus query a server with alarge enough set of images of objects, \eg, obtained from the Internet, andsome of them will be localized. The attacker can thus learn about objectplacements from the camera poses returned by the service (which is the minimalinformation returned by such a service). In this paper, we develop aproof-of-concept version of this attack and demonstrate its practicalfeasibility. The attack does not place any requirements on the localizationalgorithm used, and thus also applies to privacy-preserving representations.Current work on privacy-preserving representations alone is thus insufficient.

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