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

Robustness of deep neural networks (DNNs) to malicious perturbations is a hottopic in trustworthy AI. Existing techniques obtain robust models given fixeddatasets, either by modifying model structures, or by optimizing the process ofinference or training. While significant improvements have been made, thepossibility of constructing a high-quality dataset for model robustness remainunexplored. Follow the campaign of data-centric AI launched by Andrew Ng, wepropose a novel algorithm for dataset enhancement that works well for manyexisting DNN models to improve robustness. Transferable adversarial examplesand 14 kinds of common corruptions are included in our optimized dataset. Inthe data-centric robust learning competition hosted by Alibaba Group andTsinghua University, our algorithm came third out of more than 3000 competitorsin the first stage while we ranked fourth in the second stage. Our code isavailable at \url{https://github.com/hncszyq/tianchi_challenge}.

Exploiting the Potential of Datasets: A Data-Centric Approach for Model Robustness