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

Open-set recognition (OSR), the identification of novel categories, can be acritical component when deploying classification models in real-worldapplications. Recent work has shown that familiarity-based scoring rules suchas the Maximum Softmax Probability (MSP) or the Maximum Logit Score (MLS) arestrong baselines when the closed-set accuracy is high. However, one of thepotential weaknesses of familiarity-based OSR are adversarial attacks. Here, wepresent gradient-based adversarial attacks on familiarity scores for both typesof attacks, False Familiarity and False Novelty attacks, and evaluate theireffectiveness in informed and uninformed settings on TinyImageNet.

Familiarity-Based Open-Set Recognition Under Adversarial Attacks