Model Inversion Attacks that Exploit Confidence …

← Back to document page

Model Inversion Attacks that Exploit Confidence Informationand Basic CountermeasuresMatt FredriksonCarnegie Mellon UniversitySomesh JhaUniversity of Wisconsin MadisonThomas RistenpartCornell TechABSTRACTMachine-learning (ML) algorithms are increasingly utilizedin privacy-sensitive applications such as predicting lifestylechoices, making medical diagnoses, and facial recognition. Ina Model Inversion attack, recently introduced in a case studyof linear classifiers in personalized medicine by Fredriksonet al. [13], adversarial access to an ML Model is abusedto learn sensitive genomic information about Model Inversion Attacks apply to settings outsidetheirs, however, is develop a new class of Model Inversion attack thatexploits confidence values revealed along with new Attacks are applicable in a variety of settings, andwe explore two in depth: decision trees for lifestyle surveysas used on machine-learning-as-a-service systems and neuralnetworks for facial recognition.

countermeasures, investigating a privacy-aware decision tree training algorithm that is a simple variant of CART learn-ing, as well as revealing only rounded con dence values. The lesson that emerges is that one can avoid these kinds of MI attacks with negligible degradation to utility. 1. INTRODUCTION

  Model, Countermeasures, That, Attacks, Inversion, Exploits, Model inversion attacks that exploit