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

Deep neural networks have been shown to suffer from critical vulnerabilitiesunder adversarial attacks. This phenomenon stimulated the creation of differentattack and defense strategies similar to those adopted in cyberspace security.The dependence of such strategies on attack and defense mechanisms makes theassociated algorithms on both sides appear as closely reciprocating processes.The defense strategies are particularly passive in these processes, andenhancing initiative of such strategies can be an effective way to get out ofthis arms race. Inspired by the dynamic defense approach in cyberspace, thispaper builds upon stochastic ensemble smoothing based on defense method ofrandom smoothing and model ensemble. Proposed method employs networkarchitecture and smoothing parameters as ensemble attributes, and dynamicallychange attribute-based ensemble model before every inference predictionrequest. The proposed method handles the extreme transferability andvulnerability of ensemble models under white-box attacks. Experimentalcomparison of ASR-vs-distortion curves with different attack scenarios showsthat even the attacker with the highest attack capability cannot easily exceedthe attack success rate associated with the ensemble smoothed model, especiallyunder untargeted attacks.

Dynamic Defense Approach for Adversarial Robustness in Deep Neural Networks via Stochastic Ensemble Smoothed Model