文献データベース

On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches

Authors: Martín Abadi, Úlfar Erlingsson, Ian Goodfellow, H. Brendan McMahan, Ilya Mironov, Nicolas Papernot, Kunal Talwar, Li Zhang | Published: 2017-08-26
データプライバシー管理
プライバシー保護機械学習
差分プライバシー

Plausible Deniability for Privacy-Preserving Data Synthesis

Authors: Vincent Bindschaedler, Reza Shokri, Carl A. Gunter | Published: 2017-08-26
プライバシー保護手法
モデル性能評価
生成モデル

Modular Learning Component Attacks: Today’s Reality, Tomorrow’s Challenge

Authors: Xinyang Zhang, Yujie Ji, Ting Wang | Published: 2017-08-25
モデル抽出攻撃
ロジックロッキング
攻撃手法

Knock Knock, Who’s There? Membership Inference on Aggregate Location Data

Authors: Apostolos Pyrgelis, Carmela Troncoso, Emiliano De Cristofaro | Published: 2017-08-21 | Updated: 2017-11-29
プライバシー保護手法
プライバシー損失分析
ユーザ行動分析

Evasion Attacks against Machine Learning at Test Time

Authors: Battista Biggio, Igino Corona, Davide Maiorca, Blaine Nelson, Nedim Srndic, Pavel Laskov, Giorgio Giacinto, Fabio Roli | Published: 2017-08-21
マシン・アンラーニング
ロバスト性分析
攻撃手法

Secure Search on the Cloud via Coresets and Sketches

Authors: Adi Akavia, Dan Feldman, Hayim Shaul | Published: 2017-08-19
プライバシー保護手法
安全な算術計算
数理的解析

Learning Universal Adversarial Perturbations with Generative Models

Authors: Jamie Hayes, George Danezis | Published: 2017-08-17 | Updated: 2018-01-05
モデルの頑健性保証
攻撃手法
敵対的サンプル

Continuous User Authentication via Unlabeled Phone Movement Patterns

Authors: Rajesh Kumar, Partha Pratim Kundu, Diksha Shukla, Vir V. Phoha | Published: 2017-08-15
データ収集手法
モデル性能評価
ユーザ行動分析

ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models

Authors: Pin-Yu Chen, Huan Zhang, Yash Sharma, Jinfeng Yi, Cho-Jui Hsieh | Published: 2017-08-14 | Updated: 2017-11-02
ポイズニング
モデルの頑健性保証
攻撃手法

Cascade Adversarial Machine Learning Regularized with a Unified Embedding

Authors: Taesik Na, Jong Hwan Ko, Saibal Mukhopadhyay | Published: 2017-08-08 | Updated: 2018-03-17
ロバスト性分析
攻撃手法
敵対的学習