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

Adversarial attacks have rendered high security risks on modern deep learningsystems. Adversarial training can significantly enhance the robustness ofneural network models by suppressing the non-robust features. However, themodels often suffer from significant accuracy loss on clean data. Ensembletraining methods have emerged as promising solutions for defending againstadversarial attacks by diversifying the vulnerabilities among the sub-models,simultaneously maintaining comparable accuracy as standard training. However,existing ensemble methods are with poor scalability, owing to the rapidcomplexity increase when including more sub-models in the ensemble. Moreover,in real-world applications, it is difficult to deploy an ensemble with multiplesub-models, owing to the tight hardware resource budget and latencyrequirement. In this work, we propose ensemble-in-one (EIO), a simple butefficient way to train an ensemble within one random gated network (RGN). EIOaugments the original model by replacing the parameterized layers withmulti-path random gated blocks (RGBs) to construct a RGN. By diversifying thevulnerability of the numerous paths within the RGN, better robustness can beachieved. It provides high scalability because the paths within an EIO networkexponentially increase with the network depth. Our experiments demonstrate thatEIO consistently outperforms previous ensemble training methods with even lesscomputational overhead.

Ensemble-in-One: Learning Ensemble within Random Gated Networks for Enhanced Adversarial Robustness