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

We explore the concept of co-design in the context of neural networkverification. Specifically, we aim to train deep neural networks that not onlyare robust to adversarial perturbations but also whose robustness can beverified more easily. To this end, we identify two properties of network models- weight sparsity and so-called ReLU stability - that turn out to significantlyimpact the complexity of the corresponding verification task. We demonstratethat improving weight sparsity alone already enables us to turn computationallyintractable verification problems into tractable ones. Then, improving ReLUstability leads to an additional 4-13x speedup in verification times. Animportant feature of our methodology is its "universality," in the sense thatit can be used with a broad range of training procedures and verificationapproaches.

Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability