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 empowered accurate device-free human activityrecognition, which has wide applications. Deep models can extract robustfeatures from various sensors and generalize well even in challengingsituations such as data-insufficient cases. However, these systems could bevulnerable to input perturbations, i.e. adversarial attacks. We empiricallydemonstrate that both black-box Gaussian attacks and modern adversarialwhite-box attacks can render their accuracies to plummet. In this paper, wefirstly point out that such phenomenon can bring severe safety hazards todevice-free sensing systems, and then propose a novel learning framework,SecureSense, to defend common attacks. SecureSense aims to achieve consistentpredictions regardless of whether there exists an attack on its input or not,alleviating the negative effect of distribution perturbation caused byadversarial attacks. Extensive experiments demonstrate that our proposed methodcan significantly enhance the model robustness of existing deep models,overcoming possible attacks. The results validate that our method works well onwireless human activity recognition and person identification systems. To thebest of our knowledge, this is the first work to investigate adversarialattacks and further develop a novel defense framework for wireless humanactivity recognition in mobile computing research.

SecureSense: Defending Adversarial Attack for Secure Device-Free Human Activity Recognition