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

Many practical applications, e.g., content based image retrieval and objectrecognition, heavily rely on the local features extracted from the query image.As these local features are usually exposed to untrustworthy parties, theprivacy leakage problem of image local features has received increasingattention in recent years. In this work, we thoroughly evaluate the privacyleakage of Scale Invariant Feature Transform (SIFT), which is one of the mostwidely-used image local features. We first consider the case that the adversarycan fully access the SIFT features, i.e., both the SIFT descriptors and thecoordinates are available. We propose a novel end-to-end, coarse-to-fine deepgenerative model for reconstructing the latent image from its SIFT features.The designed deep generative model consists of two networks, where the firstone attempts to learn the structural information of the latent image bytransforming from SIFT features to Local Binary Pattern (LBP) features, whilethe second one aims to reconstruct the pixel values guided by the learned LBP.Compared with the state-of-the-art algorithms, the proposed deep generativemodel produces much improved reconstructed results over three public datasets.Furthermore, we address more challenging cases that only partial SIFT features(either SIFT descriptors or coordinates) are accessible to the adversary. It isshown that, if the adversary can only have access to the SIFT descriptors whilenot their coordinates, then the modest success of reconstructing the latentimage can be achieved for highly-structured images (e.g., faces) and would failin general settings. In addition, the latent image can be reconstructed withreasonably good quality solely from the SIFT coordinates. Our results wouldsuggest that the privacy leakage problem can be largely avoided if the SIFTcoordinates can be well protected.

Privacy Leakage of SIFT Features via Deep Generative Model based Image Reconstruction