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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Increasing use of machine learning (ML) technologies in privacy-sensitivedomains such as medical diagnoses, lifestyle predictions, and businessdecisions highlights the need to better understand if these ML technologies areintroducing leakage of sensitive and proprietary training data. In this paper,we focus on model inversion attacks where the adversary knows non-sensitiveattributes about records in the training data and aims to infer the value of asensitive attribute unknown to the adversary, using only black-box access tothe target classification model. We first devise a novel confidence score-basedmodel inversion attribute inference attack that significantly outperforms thestate-of-the-art. We then introduce a label-only model inversion attack thatrelies only on the model's predicted labels but still matches our confidencescore-based attack in terms of attack effectiveness. We also extend our attacksto the scenario where some of the other (non-sensitive) attributes of a targetrecord are unknown to the adversary. We evaluate our attacks on two types ofmachine learning models, decision tree and deep neural network, trained onthree real datasets. Moreover, we empirically demonstrate the disparatevulnerability of model inversion attacks, i.e., specific groups in the trainingdataset (grouped by gender, race, etc.) could be more vulnerable to modelinversion attacks.

Are Your Sensitive Attributes Private? Novel Model Inversion Attribute Inference Attacks on Classification Models