ml-poster
Stealing Machine Learning Models via Prediction APIs FlorianTramèr1, Fan Zhang2,Ari Juels3,Michael Reiter4,Thomas Ristenpart3 1EPFL, 2Cornell, 3CornellTech, 4UNC http://silver.web.unc.edu Cloud Security Horizons Summit, March 2016 Goals Approach cont. Results Approach § Machine learning models may be deemed confidential due to § Sensitive training data § Commercial value § Use in security applicat
Stealing Machine Learning Models via Prediction APIs
Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query interfaces. ML-as-a-service ("predictive analytics") systems are an example: Some allow users to train models on potentially sensitive data and charge others for
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
処理を実行中です
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
