Transcription of Model Inversion Attacks that Exploit Confidence …
{{id}} {{{paragraph}}}
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.
model descriptions include more information than leveraged in the black-box attack. In particular, they provide the count of instances from the training set that match each path in the decision tree. Dividing by the total number of instances gives a con dence in the classi cation. While a priori this additional information may seem innocuous, we
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}