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

Outsourcing anomaly detection to third-parties can allow data owners toovercome resource constraints (e.g., in lightweight IoT devices), facilitatecollaborative analysis (e.g., under distributed or multi-party scenarios), andbenefit from lower costs and specialized expertise (e.g., of Managed SecurityService Providers). Despite such benefits, a data owner may feel reluctant tooutsource anomaly detection without sufficient privacy protection. To that end,most existing privacy solutions would face a novel challenge, i.e., preservingprivacy usually requires the difference between data entries to be eliminatedor reduced, whereas anomaly detection critically depends on that difference.Such a conflict is recently resolved under a local analysis setting withtrusted analysts (where no outsourcing is involved) through moving the focus ofdifferential privacy (DP) guarantee from "all" to only "benign" entries. Inthis paper, we observe that such an approach is not directly applicable to theoutsourcing setting, because data owners do not know which entries are "benign"prior to outsourcing, and hence cannot selectively apply DP on data entries.Therefore, we propose a novel iterative solution for the data owner togradually "disentangle" the anomalous entries from the benign ones such thatthe third-party analyst can produce accurate anomaly results with sufficient DPguarantee. We design and implement our Differentially Private Outsourcing ofAnomaly Detection (DPOAD) framework, and demonstrate its benefits over baselineLaplace and PainFree mechanisms through experiments with real data fromdifferent application domains.

DPOAD: Differentially Private Outsourcing of Anomaly Detection through Iterative Sensitivity Learning