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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Universal adversarial perturbation attacks are widely used to analyze imageclassifiers that employ convolutional neural networks. Nowadays, some attackscan deceive image- and video-quality metrics. So sustainability analysis ofthese metrics is important. Indeed, if an attack can confuse the metric, anattacker can easily increase quality scores. When developers of image- andvideo-algorithms can boost their scores through detached processing, algorithmcomparisons are no longer fair. Inspired by the idea of universal adversarialperturbation for classifiers, we suggest a new method to attack differentiableno-reference quality metrics through universal perturbation. We applied thismethod to seven no-reference image- and video-quality metrics (PaQ-2-PiQ,Linearity, VSFA, MDTVSFA, KonCept512, Nima and SPAQ). For each one, we traineda universal perturbation that increases the respective scores. We also proposea method for assessing metric stability and identify the metrics that are themost vulnerable and the most resistant to our attack. The existence ofsuccessful universal perturbations appears to diminish the metric's ability toprovide reliable scores. We therefore recommend our proposed method as anadditional verification of metric reliability to complement traditionalsubjective tests and benchmarks.

Universal Perturbation Attack on Differentiable No-Reference Image- and Video-Quality Metrics