Privacidade diferencial em machine learning com a TensorFlow Privacy avaliações

Jinwook G. · Revisado há over 1 year

Adnan S. · Revisado há over 1 year

Eoin K. · Revisado há over 1 year

수빈 박. · Revisado há over 1 year

Kyoungeun L. · Revisado há over 1 year

지윤 임. · Revisado há over 1 year

Alexey S. · Revisado há over 1 year

현주 나. · Revisado há over 1 year

Hikam M. · Revisado há over 1 year

KIHYEON J. · Revisado há over 1 year

GEONWOO S. · Revisado há over 1 year

motioner D. · Revisado há over 1 year

정원 문. · Revisado há over 1 year

하 유. · Revisado há over 1 year

용성 이. · Revisado há over 1 year

Charlie K. · Revisado há over 1 year

혁 이. · Revisado há over 1 year

Yuchieh Cheng 鄭宇傑 E. · Revisado há over 1 year

Leslie M. · Revisado há over 1 year

Sohyun K. · Revisado há over 1 year

123

Emir S. · Revisado há over 1 year

가현 이. · Revisado há over 1 year

euiseok l. · Revisado há over 1 year

영집 김. · Revisado há over 1 year

Introduction to the topic of Privacy Budget was useful. However, the lab would have been more effective if the lab adopted the following approach: 1) Train the model using Privacy Budget n 2) Test the results 3) Retrain the model using Privacy Budget n+delta 4) Test the results 5) Observe the difference in model behaviour between the model using Privacy Budget n vs the model behaviour using Privacy Budget n+delta This would allow the lab user to observe that a lower privacy budget bounds more tightly an adversary's ability to improve their guess.

Paul C. · Revisado há over 1 year