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 robustness is a key concept in measuring the ability of neuralnetworks to defend against adversarial attacks during the inference phase.Recent studies have shown that despite the success of improving adversarialrobustness against a single type of attack using robust training techniques,models are still vulnerable to diversified $\ell_p$ attacks. To achievediversified $\ell_p$ robustness, we propose a novel robust mode connectivity(RMC)-oriented adversarial defense that contains two population-based learningphases. The first phase, RMC, is able to search the model parameter spacebetween two pre-trained models and find a path containing points with highrobustness against diversified $\ell_p$ attacks. In light of the effectivenessof RMC, we develop a second phase, RMC-based optimization, with RMC serving asthe basic unit for further enhancement of neural network diversified $\ell_p$robustness. To increase computational efficiency, we incorporate learning witha self-robust mode connectivity (SRMC) module that enables the fastproliferation of the population used for endpoints of RMC. Furthermore, we drawparallels between SRMC and the human immune system. Experimental results onvarious datasets and model architectures demonstrate that the proposed defensemethods can achieve high diversified $\ell_p$ robustness against $\ell_\infty$,$\ell_2$, $\ell_1$, and hybrid attacks. Codes are available at\url{https://github.com/wangren09/MCGR}.

Robust Mode Connectivity-Oriented Adversarial Defense: Enhancing Neural Network Robustness Against Diversified $\ell_p$ Attacks