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

The success of DNNs has driven the extensive applications of personre-identification (ReID) into a new era. However, whether ReID inherits thevulnerability of DNNs remains unexplored. To examine the robustness of ReIDsystems is rather important because the insecurity of ReID systems may causesevere losses, e.g., the criminals may use the adversarial perturbations tocheat the CCTV systems. In this work, we examine the insecurity of currentbest-performing ReID models by proposing a learning-to-mis-rank formulation toperturb the ranking of the system output. As the cross-dataset transferabilityis crucial in the ReID domain, we also perform a back-box attack by developinga novel multi-stage network architecture that pyramids the features ofdifferent levels to extract general and transferable features for theadversarial perturbations. Our method can control the number of maliciouspixels by using differentiable multi-shot sampling. To guarantee theinconspicuousness of the attack, we also propose a new perception loss toachieve better visual quality. Extensive experiments on four of the largestReID benchmarks (i.e., Market1501 [45], CUHK03 [18], DukeMTMC [33], and MSMT17[40]) not only show the effectiveness of our method, but also providesdirections of the future improvement in the robustness of ReID systems. Forexample, the accuracy of one of the best-performing ReID systems drops sharplyfrom 91.8% to 1.4% after being attacked by our method. Some attack results areshown in Fig. 1. The code is available athttps://github.com/whj363636/Adversarial-attack-on-Person-ReID-With-Deep-Mis-Ranking.

Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking