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 (DNNs) have become the essential components for variouscommercialized machine learning services, such as Machine Learning as a Service(MLaaS). Recent studies show that machine learning services face severe privacythreats - well-trained DNNs owned by MLaaS providers can be stolen throughpublic APIs, namely model stealing attacks. However, most existing worksundervalued the impact of such attacks, where a successful attack has toacquire confidential training data or auxiliary data regarding the victim DNN.In this paper, we propose ES Attack, a novel model stealing attack without anydata hurdles. By using heuristically generated synthetic data, ES Attackiteratively trains a substitute model and eventually achieves a functionallyequivalent copy of the victim DNN. The experimental results reveal the severityof ES Attack: i) ES Attack successfully steals the victim model without datahurdles, and ES Attack even outperforms most existing model stealing attacksusing auxiliary data in terms of model accuracy; ii) most countermeasures areineffective in defending ES Attack; iii) ES Attack facilitates further attacksrelying on the stolen model.

ES Attack: Model Stealing against Deep Neural Networks without Data Hurdles