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

The goal of Domain Generation Algorithm (DGA) detection is to recognizeinfections with bot malware and is often done with help of Machine Learningapproaches that classify non-resolving Domain Name System (DNS) traffic and aretrained on possibly sensitive data. In parallel, the rise of privacy researchin the Machine Learning world leads to privacy-preserving measures that aretightly coupled with a deep learning model's architecture or training routine,while non deep learning approaches are commonly better suited for theapplication of privacy-enhancing methods outside the actual classificationmodule. In this work, we aim to measure the privacy capability of the featureextractor of feature-based DGA detector FANCI (Feature-based Automated NxdomainClassification and Intelligence). Our goal is to assess whether a data-richadversary can learn an inverse mapping of FANCI's feature extractor and therebyreconstruct domain names from feature vectors. Attack success would pose aprivacy threat to sharing FANCI's feature representation, while the oppositewould enable this representation to be shared without privacy concerns. Usingthree real-world data sets, we train a recurrent Machine Learning model on thereconstruction task. Our approaches result in poor reconstruction performanceand we attempt to back our findings with a mathematical review of the featureextraction process. We thus reckon that sharing FANCI's feature representationdoes not constitute a considerable privacy leakage.

Sharing FANCI Features: A Privacy Analysis of Feature Extraction for DGA Detection