Transcription of Model Inversion Attacks that Exploit Confidence …
{{id}} {{{paragraph}}}
Example: air traffic controller
Model Inversion Attacks that Exploit Confidence …
Model Inversion Attacks that Exploit Confidence Informationand Basic CountermeasuresMatt FredriksonCarnegie Mellon UniversitySomesh JhaUniversity of Wisconsin MadisonThomas RistenpartCornell TechABSTRACTM achine-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.
di erent BigML decision tree models. This high precision holds for target subjects who are known to be in the training data, while the estimator’s precision is signi cantly worse for those not in the training data set. This demonstrates that publishing these models poses a privacy risk for those contributing to the training data.
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: